dda5dedf44
- build.mjs no longer writes bench.html, journey.html or journey.json; the three files are deleted; /bench -> /evidence and /journey -> /live redirects (permanent: false); nav, footer, sitemap, capture routes and the site-nav-check groups drop them; link-check resolves literal vercel.json redirects and lists every link that leans on one (evidence.html: /bench, another hand) - every testnet card, column, row, notice and link removed from the pages this lane owns; release manifest: the testnet entry gone, network igneum-devnet-4 "Igneum 2.0 devnet", the Devnet 3 genesis, digest, vote domain and floor lines dropped - "Devnet 3" leaves every owned page; the devnet state is one constant in build.mjs (DEVNET_STATE, 'starting' now: the nav pill and the homepage badge read "Igneum 2.0 devnet starting"; 'live' flips both and re-enables the nav's live read) - no 0.x release history: screenshot alt texts say the current build, the miner page's "Current build:" keeps the data-rm spans without the node version; miner-bench.json keeps the current-program rows only, no Counter ASIC names, no versions; /miners drops the earlier-classes table, the history note and the miner-version column - /income keeps the calculator; the testnet-era tier tables (docs/analysis/income-tiers.md) are not served - the positioning line is the first line of the footer partial (every page), the homepage meta description's first sentence and the hero's sub-line; share metas (site/og/pages.mjs) carry no Devnet 3 or zkEVM - ledger-text-check is red on two index.html pins (X2, X31: the testnet sentences), owned by the ledger hand Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
1198 lines
86 KiB
JSON
1198 lines
86 KiB
JSON
{
|
||
"_about": "Rows of the public bench table at /miners (site/build.mjs). One row per card on the current program: the best measured rate. Later jobs append rows. Fields: card, generator (v1 | v2), mh_s (best measured MH/s), mh_per_w (MH per watt, null when the power was not measured), miner (the miner or package version), date (YYYY-MM-DD), source (the docs/bench-log.md heading, or the job id), by ('measured by the team' | 'reported by the fleet'), note (short, optional), watts (board power at the rate, null when not read), v4_cost (what the class v4 shadow costs this card against the class v3 control: watts and rate, measured; 'not measured' when not), tuned (the card's tune state at the row: 'full Ember Tune: <point>' | 'clock lock <MHz>, cap <W>' | 'stock, bench only' | 'stock, mining'), driver_os (driver and OS where known). No machine names, no addresses, no owner names: the build scrubs the page and fails on any that survive. hive (the copy-in HiveOS flight-sheet values at the row's tune point: core MHz (a lock), mem MHz, pl W; each labelled measured with the date, or 'stock' where no tune point exists). group ('buy' | 'datacentre'); watt_basis ('chip' when the watts are the chip's, not the wall's); v4_short (the one-clause class v4 figure for the column).",
|
||
"rows": [
|
||
{
|
||
"card": "NVIDIA RTX 5060 Ti (16 GB)",
|
||
"generator": "v2",
|
||
"mh_s": 30.9,
|
||
"mh_per_w": 0.269,
|
||
"miner": "Igneum Miner package, prebuilt NVRTC worker (bench mode, class v4 program)",
|
||
"date": "2026-10-07",
|
||
"source": "bench log: 7 October 2026, the first 16 GB card: an RTX 5060 Ti in a Thunderbolt enclosure (run b)",
|
||
"by": "measured by the team",
|
||
"note": "class v4 program, 128 loads per hash, 1 GiB dataset, 10-minute window on the card alone at the stock 180 W limit: 114.8 W mean; PCIe 4.0 x4 through the enclosure",
|
||
"watts": 114.8,
|
||
"v4_cost": "0.1 percent of rate, measured 7 October 2026",
|
||
"driver_os": "NVIDIA driver, Windows 11",
|
||
"tuned": "stock, bench only (180 W default cap, never tuned)",
|
||
"hive": {
|
||
"core_mhz": null,
|
||
"mem_mhz": null,
|
||
"pl_w": null,
|
||
"label": "stock (no measured tune point; the 5080 and 9070 XT passes and the class v4 efficiency pass land theirs when read)"
|
||
},
|
||
"group": "buy"
|
||
},
|
||
{
|
||
"card": "NVIDIA RTX 5090 (32 GB)",
|
||
"generator": "v2",
|
||
"mh_s": 136.1,
|
||
"watts": 226.8,
|
||
"mh_per_w": 0.563,
|
||
"miner": "Igneum Miner + Ember Tune kit 6 (mining, class v3 program)",
|
||
"date": "2026-10-06",
|
||
"source": "bench log: 6 October 2026, Ember run 6; the chip-model measurement record: item 8's 5090 rows and the class v4 efficiency pass (7 October 2026)",
|
||
"by": "measured by the team",
|
||
"note": "one row for the card: best rate 136.1 MH/s at 350 W stock unlocked on the class v3 control (bench, 6 October 2026); best MH per wall watt 127.71 MH/s at 226.8 W at the full Ember Tune point, 1,854 MHz (Ember run 6, 6 October 2026); the class v4 efficiency pass (7 October 2026, 60 s steps, every fingerprint matched): unlocked 136.84 MH/s at 475.5 W (0.288), the 1,400 MHz lock 134.98 at 316.3 W (0.427), the knee 1,300 MHz, the best point 1,200 MHz 133.80 at 305.1 W (0.439); the fleet's standing 5090 reads 100.6 MH/s at 308 W beside its prover (reported by the fleet)",
|
||
"v4_cost": "class v4 at the 1,200 MHz knee: 133.80 MH/s at 305.1 W (0.439 MH/W); the premium over class v3 81.8 W at the best points and 145.3 W unlocked, measured 7 October 2026",
|
||
"tuned": "full Ember Tune: 1,854 MHz core lock at the 100 percent cap",
|
||
"driver_os": "NVIDIA driver, Windows 11",
|
||
"hive": {
|
||
"core_mhz": 1854,
|
||
"mem_mhz": 13801,
|
||
"pl_w": 460,
|
||
"label": "measured 6 October 2026 (Ember run 6: the clock lock 1,854 MHz, the memory clock as read, the limit 460 W of 575 as the cap did not bind)"
|
||
},
|
||
"v4_short": "133.8 MH/s, 305 W, 0.439",
|
||
"group": "buy",
|
||
"mh_s_display": "136.1 stock (127.7 tuned)",
|
||
"watts_display": "226.8 tuned (350 stock)"
|
||
},
|
||
{
|
||
"card": "NVIDIA RTX 4070 (12 GB)",
|
||
"generator": "v2",
|
||
"mh_s": 30.95,
|
||
"watts": 79.5,
|
||
"mh_per_w": 0.389,
|
||
"miner": "igneum-worker-cuda bench (installed worker), class v3 control",
|
||
"date": "2026-10-06",
|
||
"source": "the chip-model measurement record: item 8, the RTX 4070 rows (job run-ca3-pc1-4070-shadow-20261006)",
|
||
"by": "measured by the team",
|
||
"note": "79.3 to 79.8 W at the tune point; 28.78 MH/s at 75.6 W (0.381) in Ember run 6 mining",
|
||
"v4_cost": "+30 W (79 to 109 W) for +0.4 percent of rate at 102,100 ops per hash, measured 6 October 2026",
|
||
"tuned": "full Ember Tune: 1,860 MHz core lock, 160 W cap (Ember run 6: 1,863 MHz at the 50 percent cap, 75.6 W)",
|
||
"driver_os": "NVIDIA driver, Windows 11",
|
||
"hive": {
|
||
"core_mhz": 1863,
|
||
"mem_mhz": 10251,
|
||
"pl_w": 100,
|
||
"label": "measured 6 October 2026 (Ember run 6: 1,863 MHz at the 50 percent cap of 200 W, 75.6 W drawn; the item 8 rows at 1,860 MHz and 160 W)"
|
||
},
|
||
"group": "buy"
|
||
},
|
||
{
|
||
"card": "AMD Radeon RX 9070 XT (16 GB)",
|
||
"generator": "v2",
|
||
"mh_s": 18.96,
|
||
"watts": 149.3,
|
||
"mh_per_w": 0.127,
|
||
"miner": "igneum-worker-opencl bench (installed worker), class v3 control",
|
||
"date": "2026-10-08",
|
||
"source": "the chip-model measurement record: the RX 9070 XT's first measured grid on the AMD knob (job run-ca3-pc1-amd-grid-9070-20261008-b, 24 of 24 points, 8 October 2026) for the rate and the watts; the 9070 XT Ember tune row (run-ca3-pc1-ember-9070-20261007) for the app's own stock reading",
|
||
"by": "measured by the team",
|
||
"note": "the grid's stock point reads 3,292 MHz, 195.8 W, 0.097 MH per watt (the app's own stock reading of 7 October was 202 W); the clock offset alone reaches 2,924 MHz at 159.2 W and the power limit alone 184.4 W; the best point is both together. Against the 5090 at its class v4 1,200 MHz lock (133.8 MH/s at 305 W, 0.43 MH per watt) the 9070 XT at its best point sits 3.5x behind per watt; against the 5090 at its 1,300 MHz knee (134.6 at 223 W, 0.60) about a fifth",
|
||
"v4_cost": "+2 percent of rate (19.29 against 18.92 MH/s) at 102,100 ops per hash, watts owed, measured 6 October 2026",
|
||
"tuned": "core -500 MHz, power -30 percent, with the AMD knob: 2,921 MHz, 149.3 W at 18.96 MH/s, a 24 percent saving at the same rate (the rate flat at 18.93 to 18.98 MH/s on all 24 points, the knob moves watts only); measured 8 October 2026",
|
||
"driver_os": "Adrenalin 26.9.2, Windows 11",
|
||
"hive": {
|
||
"core_mhz": null,
|
||
"mem_mhz": null,
|
||
"pl_w": null,
|
||
"label": "the AMD knob is the app’s (core -500 MHz, power -30 percent); no Hive flight-sheet values yet"
|
||
},
|
||
"group": "buy",
|
||
"mh_s_display": "19.0 stock (19.0 with the AMD knob)",
|
||
"watts_display": "149.3 with the AMD knob (195.8 stock)"
|
||
},
|
||
{
|
||
"card": "Apple M5 Max (40 GPU cores, Metal)",
|
||
"generator": "v2",
|
||
"mh_s": 27,
|
||
"watts": 21,
|
||
"mh_per_w": 1.29,
|
||
"miner": "igneum-miner Metal worker, class v3 program",
|
||
"date": "2026-10-06",
|
||
"source": "the chip-model measurement record: item 8, the Mac rows (IOReport GPU and DRAM watts)",
|
||
"by": "measured by the team",
|
||
"note": "GPU plus DRAM watts from IOReport, not wall power, so its MH per watt is not ranked against the cards' wall figures",
|
||
"v4_cost": "+16 W for 1.5 percent of rate at 102,100 ops per hash, measured 6 October 2026",
|
||
"tuned": "no lever on Apple silicon (no clock or power control exposed); stock",
|
||
"driver_os": "macOS, Metal",
|
||
"hive": {
|
||
"core_mhz": null,
|
||
"mem_mhz": null,
|
||
"pl_w": null,
|
||
"label": "stock (no measured tune point; the 5080 and 9070 XT passes and the class v4 efficiency pass land theirs when read)"
|
||
},
|
||
"watt_basis": "chip",
|
||
"group": "buy"
|
||
},
|
||
{
|
||
"card": "Intel Arc B580 (12 GB)",
|
||
"generator": "v2",
|
||
"mh_s": 11,
|
||
"watts": null,
|
||
"mh_per_w": null,
|
||
"miner": "igneum-worker-opencl bench, class v4 program",
|
||
"date": "2026-10-07",
|
||
"source": "bench log: 7 October 2026, the Intel Arc B580 (eGPU equals slot)",
|
||
"by": "measured by the team",
|
||
"note": "the same rate in the Thunderbolt enclosure and the slot; watts not read on this run. Re-read 8 October 2026: the installed OpenCL worker on this card passes its own self-test with the devnet pack (96 of 96 vector lanes) and mined 54 CPU-re-checked blocks at 10.58 MH/s, so the row stands; a kit build from a branch without the Intel rotate-fold rewrite failed its self-test on this card the same morning, a build fault and not an Arc result",
|
||
"v4_cost": "0.1 percent of rate, measured 7 October 2026",
|
||
"tuned": "stock, bench only",
|
||
"driver_os": "Intel driver, Windows 11",
|
||
"hive": {
|
||
"core_mhz": null,
|
||
"mem_mhz": null,
|
||
"pl_w": null,
|
||
"label": "stock (no measured tune point; the 5080 and 9070 XT passes and the class v4 efficiency pass land theirs when read)"
|
||
},
|
||
"group": "buy"
|
||
},
|
||
{
|
||
"card": "NVIDIA H100 SXM (80 GB)",
|
||
"generator": "v2",
|
||
"mh_s": 248.7,
|
||
"watts": 385.6,
|
||
"mh_per_w": 0.645,
|
||
"miner": "igneum-worker-cuda bench (Linux), class v3 control",
|
||
"date": "2026-10-07",
|
||
"source": "bench log: 7 October 2026, every rentable card on the hash (the fleet's sweep, a rented card)",
|
||
"by": "measured by the fleet",
|
||
"note": "424.0 W maximum; 98 percent of its random-read ceiling like the 5090; 1.78x the 5090's hash at 1.15x the tuned 5090's hash per watt and a third of the hash per rented dollar. Watts are class v3 (read 8 October 2026, 11:4x UK): the fleet's bench pack was the class v3 program (program_class v3, generator 3, load_class mx8-erad810f22d), so this row's watts and MH per watt are class v3 figures; the rate holds under class v4 (memory-bound: a 5070 Ti measured 78.7 MH/s at 141 W on class v3 and 78.8 at 224 W on class v4). The class v4 watts rerun on the same models lands with its date, the v3 watts kept beside as the shadow premium per card",
|
||
"v4_cost": "not measured",
|
||
"tuned": "stock, bench only (rented, not tuned)",
|
||
"driver_os": "NVIDIA driver 580.126.09, Ubuntu 24.04",
|
||
"hive": {
|
||
"core_mhz": null,
|
||
"mem_mhz": null,
|
||
"pl_w": null,
|
||
"label": "stock (no measured tune point; the 5080 and 9070 XT passes and the class v4 efficiency pass land theirs when read)"
|
||
},
|
||
"group": "datacentre",
|
||
"watts_class": "v3",
|
||
"watts_display": "385.6 (class v3)"
|
||
},
|
||
{
|
||
"card": "NVIDIA RTX 5080 (16 GB)",
|
||
"generator": "v2",
|
||
"mh_s": 71.2,
|
||
"watts": 146.6,
|
||
"mh_per_w": 0.486,
|
||
"miner": "the runner's card switch, class v4 program (job run-ca3-pc1-v4-eff-5080-20261007-d)",
|
||
"date": "2026-10-08",
|
||
"source": "bench log: 7 to 8 October 2026, the class v4 efficiency passes: the core clock lock on the RTX 5090 and the RTX 5080",
|
||
"by": "measured by the team",
|
||
"note": "the knee sits between 1,000 and 900 MHz (the rate within 0.3 percent of unlocked down to 1,000 MHz, 5.2 percent off at 900 on class v4); the draw floors from 1,500 MHz down. The rented fleet's 5080 read 71.16 MH/s at 143.4 W stock (the hive package, Ubuntu 24.04, 7 October 2026), 110 W under this card's stock draw: the method differs per row (nvidia-smi on Linux, the runner's card switch on Windows) and neither is taken as the card's figure until the fleet re-measures",
|
||
"v4_cost": "83.4 W unlocked and 41 W at the best points for 0.2 percent of rate (class v4 71.41 MH/s at 253.1 W against class v3 71.28 at 169.7 W unlocked; measured 8 October 2026)",
|
||
"tuned": "core lock 1,100 MHz (the efficiency pass's best point: 71.20 MH/s at 146.6 W, 0.486 MH/W, 106.5 W recovered for 0.29 percent of rate), memory 14,801 MHz, the driver's power limit untouched",
|
||
"driver_os": "NVIDIA driver 617.14, Windows 11",
|
||
"hive": {
|
||
"core_mhz": 1100,
|
||
"mem_mhz": null,
|
||
"pl_w": null,
|
||
"label": "core lock 1,100 MHz, memory stock, power limit untouched (measured 8 October 2026, the efficiency pass)"
|
||
},
|
||
"group": "buy",
|
||
"mh_s_display": "71.4 stock (71.2 tuned)",
|
||
"watts_display": "146.6 tuned (253 stock)",
|
||
"v4_short": "+83 W unlocked, +41 W at the best points"
|
||
},
|
||
{
|
||
"card": "NVIDIA RTX 3070 Ti (8 GB)",
|
||
"generator": "v2",
|
||
"mh_s": 38.98,
|
||
"watts": 178.3,
|
||
"mh_per_w": 0.219,
|
||
"miner": "the hive package igneum-worker-cuda, class v4 program",
|
||
"date": "2026-10-07",
|
||
"source": "bench log: 7 October 2026, every rentable card on the hash (the fleet's sweep on rented cards; the hive package, Ubuntu 24.04)",
|
||
"by": "measured by the fleet",
|
||
"note": ". Watts are class v3 (read 8 October 2026, 11:4x UK): the fleet's bench pack was the class v3 program (program_class v3, generator 3, load_class mx8-erad810f22d), so this row's watts and MH per watt are class v3 figures; the rate holds under class v4 (memory-bound: a 5070 Ti measured 78.7 MH/s at 141 W on class v3 and 78.8 at 224 W on class v4). The class v4 watts rerun on the same models lands with its date, the v3 watts kept beside as the shadow premium per card",
|
||
"v4_cost": "not measured (class v4 program only)",
|
||
"tuned": "stock, bench only (rented, not tuned)",
|
||
"driver_os": "NVIDIA driver 595.71.05, Ubuntu 24.04",
|
||
"hive": {
|
||
"core_mhz": null,
|
||
"mem_mhz": null,
|
||
"pl_w": null,
|
||
"label": "stock (no measured tune point; the 5080 and 9070 XT passes and the class v4 efficiency pass land theirs when read)"
|
||
},
|
||
"group": "buy",
|
||
"watts_class": "v3",
|
||
"watts_display": "178.3 (class v3)"
|
||
},
|
||
{
|
||
"card": "NVIDIA RTX 3070 (8 GB)",
|
||
"generator": "v2",
|
||
"mh_s": 33.66,
|
||
"watts": null,
|
||
"mh_per_w": null,
|
||
"miner": "the hive package igneum-miner, class v4 program",
|
||
"date": "2026-10-07",
|
||
"source": "a fleet canary (status line, 7 October 2026)",
|
||
"by": "reported by the fleet",
|
||
"note": "a fleet canary’s status line, 17:07Z, beside its node; watts not read",
|
||
"v4_cost": "not measured (class v4 program only)",
|
||
"tuned": "stock, mining",
|
||
"driver_os": "NVIDIA driver, Ubuntu 24.04",
|
||
"hive": {
|
||
"core_mhz": null,
|
||
"mem_mhz": null,
|
||
"pl_w": null,
|
||
"label": "stock (no measured tune point; the 5080 and 9070 XT passes and the class v4 efficiency pass land theirs when read)"
|
||
},
|
||
"group": "buy"
|
||
},
|
||
{
|
||
"card": "NVIDIA RTX 3080 (10 GB)",
|
||
"generator": "v2",
|
||
"mh_s": 43.72,
|
||
"watts": null,
|
||
"mh_per_w": null,
|
||
"miner": "the hive package igneum-miner, class v4 program",
|
||
"date": "2026-10-07",
|
||
"source": "the fleet's standing voter (status line, 7 October 2026) and the sweep's hands row",
|
||
"by": "reported by the fleet",
|
||
"note": "a standing voter's status line, 18:00Z; the hands row of the sweep reads 40.82 MH/s at 204.9 W; 10 GB, no prover",
|
||
"v4_cost": "not measured (class v4 program only)",
|
||
"tuned": "stock, mining",
|
||
"driver_os": "NVIDIA driver, Ubuntu 24.04",
|
||
"hive": {
|
||
"core_mhz": null,
|
||
"mem_mhz": null,
|
||
"pl_w": null,
|
||
"label": "stock (no measured tune point; the 5080 and 9070 XT passes and the class v4 efficiency pass land theirs when read)"
|
||
},
|
||
"group": "buy"
|
||
},
|
||
{
|
||
"card": "NVIDIA RTX 3080 Ti (12 GB)",
|
||
"generator": "v2",
|
||
"mh_s": 58.95,
|
||
"watts": 267.3,
|
||
"mh_per_w": 0.221,
|
||
"miner": "the hive package igneum-worker-cuda, class v4 program",
|
||
"date": "2026-10-07",
|
||
"source": "bench log: 7 October 2026, every rentable card on the hash (the fleet's sweep on rented cards; the hive package, Ubuntu 24.04)",
|
||
"by": "measured by the fleet",
|
||
"note": "283.0 W maximum. Watts are class v3 (read 8 October 2026, 11:4x UK): the fleet's bench pack was the class v3 program (program_class v3, generator 3, load_class mx8-erad810f22d), so this row's watts and MH per watt are class v3 figures; the rate holds under class v4 (memory-bound: a 5070 Ti measured 78.7 MH/s at 141 W on class v3 and 78.8 at 224 W on class v4). The class v4 watts rerun on the same models lands with its date, the v3 watts kept beside as the shadow premium per card",
|
||
"v4_cost": "not measured (class v4 program only)",
|
||
"tuned": "stock, bench only (rented, not tuned)",
|
||
"driver_os": "NVIDIA driver 580.65.06, Ubuntu 24.04",
|
||
"hive": {
|
||
"core_mhz": null,
|
||
"mem_mhz": null,
|
||
"pl_w": null,
|
||
"label": "stock (no measured tune point; the 5080 and 9070 XT passes and the class v4 efficiency pass land theirs when read)"
|
||
},
|
||
"group": "buy",
|
||
"watts_class": "v3",
|
||
"watts_display": "267.3 (class v3)"
|
||
},
|
||
{
|
||
"card": "NVIDIA RTX 3090 (24 GB)",
|
||
"generator": "v2",
|
||
"mh_s": 50.04,
|
||
"watts": null,
|
||
"mh_per_w": null,
|
||
"miner": "the hive package igneum-miner, class v4 program",
|
||
"date": "2026-10-07",
|
||
"source": "the fleet's standing voters (status lines, 7 October 2026)",
|
||
"by": "reported by the fleet",
|
||
"note": "the best of four standing voters this hour (42.2 to 50.0 MH/s) beside their provers; watts not read",
|
||
"v4_cost": "not measured (class v4 program only)",
|
||
"tuned": "stock, mining",
|
||
"driver_os": "NVIDIA driver, Ubuntu 24.04",
|
||
"hive": {
|
||
"core_mhz": null,
|
||
"mem_mhz": null,
|
||
"pl_w": null,
|
||
"label": "stock (no measured tune point; the 5080 and 9070 XT passes and the class v4 efficiency pass land theirs when read)"
|
||
},
|
||
"group": "buy"
|
||
},
|
||
{
|
||
"card": "NVIDIA RTX 3090 Ti (24 GB)",
|
||
"generator": "v2",
|
||
"mh_s": 61.95,
|
||
"watts": 249.5,
|
||
"mh_per_w": 0.248,
|
||
"miner": "the hive package igneum-worker-cuda, class v4 program",
|
||
"date": "2026-10-07",
|
||
"source": "bench log: 7 October 2026, every rentable card on the hash (the fleet's sweep on rented cards; the hive package, Ubuntu 24.04)",
|
||
"by": "measured by the fleet",
|
||
"note": ". Watts are class v3 (read 8 October 2026, 11:4x UK): the fleet's bench pack was the class v3 program (program_class v3, generator 3, load_class mx8-erad810f22d), so this row's watts and MH per watt are class v3 figures; the rate holds under class v4 (memory-bound: a 5070 Ti measured 78.7 MH/s at 141 W on class v3 and 78.8 at 224 W on class v4). The class v4 watts rerun on the same models lands with its date, the v3 watts kept beside as the shadow premium per card",
|
||
"v4_cost": "not measured (class v4 program only)",
|
||
"tuned": "stock, bench only (rented, not tuned)",
|
||
"driver_os": "NVIDIA driver 580.65.06, Ubuntu 24.04",
|
||
"hive": {
|
||
"core_mhz": null,
|
||
"mem_mhz": null,
|
||
"pl_w": null,
|
||
"label": "stock (no measured tune point; the 5080 and 9070 XT passes and the class v4 efficiency pass land theirs when read)"
|
||
},
|
||
"group": "buy",
|
||
"watts_class": "v3",
|
||
"watts_display": "249.5 (class v3)"
|
||
},
|
||
{
|
||
"card": "NVIDIA RTX 4090 (24 GB)",
|
||
"generator": "v2",
|
||
"mh_s": 52.25,
|
||
"watts": 183.1,
|
||
"mh_per_w": 0.285,
|
||
"miner": "the hive package igneum-worker-cuda, class v4 program",
|
||
"date": "2026-10-07",
|
||
"source": "bench log: 7 October 2026, the RTX 4090 hands row",
|
||
"by": "measured by the fleet",
|
||
"note": "the hands row: the card mines and proves (17.4 GB peak while proving); the standing 4090 voters read 44.5 to 50.8 MH/s this hour beside their provers",
|
||
"v4_cost": "not measured (class v4 program only)",
|
||
"tuned": "stock, bench only (rented, not tuned)",
|
||
"driver_os": "NVIDIA driver 580, Ubuntu 24.04",
|
||
"hive": {
|
||
"core_mhz": null,
|
||
"mem_mhz": null,
|
||
"pl_w": null,
|
||
"label": "stock (no measured tune point; the 5080 and 9070 XT passes and the class v4 efficiency pass land theirs when read)"
|
||
},
|
||
"group": "buy"
|
||
},
|
||
{
|
||
"card": "NVIDIA RTX 3060 (12 GB)",
|
||
"generator": "v2",
|
||
"mh_s": 26.89,
|
||
"watts": 111.6,
|
||
"mh_per_w": 0.241,
|
||
"miner": "the hive package igneum-worker-cuda, class v4 program",
|
||
"date": "2026-10-07",
|
||
"source": "bench log: 7 October 2026, every rentable card on the hash (the fleet's sweep on rented cards; the hive package, Ubuntu 24.04)",
|
||
"by": "measured by the fleet",
|
||
"note": "114.5 W maximum; the devnet boxes read 23.7 to 25.7 MH/s beside their nodes. Watts are class v3 (read 8 October 2026, 11:4x UK): the fleet's bench pack was the class v3 program (program_class v3, generator 3, load_class mx8-erad810f22d), so this row's watts and MH per watt are class v3 figures; the rate holds under class v4 (memory-bound: a 5070 Ti measured 78.7 MH/s at 141 W on class v3 and 78.8 at 224 W on class v4). The class v4 watts rerun on the same models lands with its date, the v3 watts kept beside as the shadow premium per card",
|
||
"v4_cost": "not measured (class v4 program only)",
|
||
"tuned": "stock, bench only (rented, not tuned)",
|
||
"driver_os": "NVIDIA driver 580.126.09, Ubuntu 24.04",
|
||
"hive": {
|
||
"core_mhz": null,
|
||
"mem_mhz": null,
|
||
"pl_w": null,
|
||
"label": "stock (no measured tune point; the 5080 and 9070 XT passes and the class v4 efficiency pass land theirs when read)"
|
||
},
|
||
"group": "buy",
|
||
"watts_class": "v3",
|
||
"watts_display": "111.6 (class v3)"
|
||
},
|
||
{
|
||
"card": "NVIDIA RTX 3060 Ti (8 GB)",
|
||
"generator": "v2",
|
||
"mh_s": 33.1,
|
||
"watts": 129.5,
|
||
"mh_per_w": 0.256,
|
||
"miner": "the hive package igneum-worker-cuda, class v4 program",
|
||
"date": "2026-10-07",
|
||
"source": "bench log: 7 October 2026, every rentable card on the hash (the fleet's sweep on rented cards; the hive package, Ubuntu 24.04)",
|
||
"by": "measured by the fleet",
|
||
"note": ". Watts are class v3 (read 8 October 2026, 11:4x UK): the fleet's bench pack was the class v3 program (program_class v3, generator 3, load_class mx8-erad810f22d), so this row's watts and MH per watt are class v3 figures; the rate holds under class v4 (memory-bound: a 5070 Ti measured 78.7 MH/s at 141 W on class v3 and 78.8 at 224 W on class v4). The class v4 watts rerun on the same models lands with its date, the v3 watts kept beside as the shadow premium per card",
|
||
"v4_cost": "not measured (class v4 program only)",
|
||
"tuned": "stock, bench only (rented, not tuned)",
|
||
"driver_os": "NVIDIA driver 580, Ubuntu 24.04",
|
||
"hive": {
|
||
"core_mhz": null,
|
||
"mem_mhz": null,
|
||
"pl_w": null,
|
||
"label": "stock (no measured tune point; the 5080 and 9070 XT passes and the class v4 efficiency pass land theirs when read)"
|
||
},
|
||
"group": "buy",
|
||
"watts_class": "v3",
|
||
"watts_display": "129.5 (class v3)"
|
||
},
|
||
{
|
||
"card": "NVIDIA RTX 4060 Ti (8 GB)",
|
||
"generator": "v2",
|
||
"mh_s": 20.1,
|
||
"watts": 77.5,
|
||
"mh_per_w": 0.259,
|
||
"miner": "the hive package igneum-worker-cuda, class v4 program",
|
||
"date": "2026-10-07",
|
||
"source": "bench log: 7 October 2026, every rentable card on the hash (the fleet's sweep on rented cards; the hive package, Ubuntu 24.04)",
|
||
"by": "measured by the fleet",
|
||
"note": ". Watts are class v3 (read 8 October 2026, 11:4x UK): the fleet's bench pack was the class v3 program (program_class v3, generator 3, load_class mx8-erad810f22d), so this row's watts and MH per watt are class v3 figures; the rate holds under class v4 (memory-bound: a 5070 Ti measured 78.7 MH/s at 141 W on class v3 and 78.8 at 224 W on class v4). The class v4 watts rerun on the same models lands with its date, the v3 watts kept beside as the shadow premium per card",
|
||
"v4_cost": "not measured (class v4 program only)",
|
||
"tuned": "stock, bench only (rented, not tuned)",
|
||
"driver_os": "NVIDIA driver 580, Ubuntu 24.04",
|
||
"hive": {
|
||
"core_mhz": null,
|
||
"mem_mhz": null,
|
||
"pl_w": null,
|
||
"label": "stock (no measured tune point; the 5080 and 9070 XT passes and the class v4 efficiency pass land theirs when read)"
|
||
},
|
||
"group": "buy",
|
||
"watts_class": "v3",
|
||
"watts_display": "77.5 (class v3)"
|
||
},
|
||
{
|
||
"card": "NVIDIA RTX 4070 Ti (12 GB)",
|
||
"generator": "v2",
|
||
"mh_s": 31.26,
|
||
"watts": 107.3,
|
||
"mh_per_w": 0.291,
|
||
"miner": "the hive package igneum-worker-cuda, class v4 program",
|
||
"date": "2026-10-07",
|
||
"source": "bench log: 7 October 2026, every rentable card on the hash (the fleet's sweep on rented cards; the hive package, Ubuntu 24.04)",
|
||
"by": "measured by the fleet",
|
||
"note": ". Watts are class v3 (read 8 October 2026, 11:4x UK): the fleet's bench pack was the class v3 program (program_class v3, generator 3, load_class mx8-erad810f22d), so this row's watts and MH per watt are class v3 figures; the rate holds under class v4 (memory-bound: a 5070 Ti measured 78.7 MH/s at 141 W on class v3 and 78.8 at 224 W on class v4). The class v4 watts rerun on the same models lands with its date, the v3 watts kept beside as the shadow premium per card",
|
||
"v4_cost": "not measured (class v4 program only)",
|
||
"tuned": "stock, bench only (rented, not tuned)",
|
||
"driver_os": "NVIDIA driver 580, Ubuntu 24.04",
|
||
"hive": {
|
||
"core_mhz": null,
|
||
"mem_mhz": null,
|
||
"pl_w": null,
|
||
"label": "stock (no measured tune point; the 5080 and 9070 XT passes and the class v4 efficiency pass land theirs when read)"
|
||
},
|
||
"group": "buy",
|
||
"watts_class": "v3",
|
||
"watts_display": "107.3 (class v3)"
|
||
},
|
||
{
|
||
"card": "NVIDIA RTX 5060 (8 GB)",
|
||
"generator": "v2",
|
||
"mh_s": 31.27,
|
||
"watts": 75.4,
|
||
"mh_per_w": 0.415,
|
||
"miner": "the hive package igneum-worker-cuda, class v4 program",
|
||
"date": "2026-10-07",
|
||
"source": "bench log: 7 October 2026, every rentable card on the hash (the fleet's sweep on rented cards; the hive package, Ubuntu 24.04)",
|
||
"by": "measured by the fleet",
|
||
"note": ". Watts are class v3 (read 8 October 2026, 11:4x UK): the fleet's bench pack was the class v3 program (program_class v3, generator 3, load_class mx8-erad810f22d), so this row's watts and MH per watt are class v3 figures; the rate holds under class v4 (memory-bound: a 5070 Ti measured 78.7 MH/s at 141 W on class v3 and 78.8 at 224 W on class v4). The class v4 watts rerun on the same models lands with its date, the v3 watts kept beside as the shadow premium per card",
|
||
"v4_cost": "not measured (class v4 program only)",
|
||
"tuned": "stock, bench only (rented, not tuned)",
|
||
"driver_os": "NVIDIA driver 580, Ubuntu 24.04",
|
||
"hive": {
|
||
"core_mhz": null,
|
||
"mem_mhz": null,
|
||
"pl_w": null,
|
||
"label": "stock (no measured tune point; the 5080 and 9070 XT passes and the class v4 efficiency pass land theirs when read)"
|
||
},
|
||
"group": "buy",
|
||
"watts_class": "v3",
|
||
"watts_display": "75.4 (class v3)"
|
||
},
|
||
{
|
||
"card": "NVIDIA RTX 5070 (12 GB)",
|
||
"generator": "v2",
|
||
"mh_s": 52.01,
|
||
"watts": 102.8,
|
||
"mh_per_w": 0.506,
|
||
"miner": "the hive package igneum-worker-cuda, class v4 program",
|
||
"date": "2026-10-07",
|
||
"source": "bench log: 7 October 2026, every rentable card on the hash (the fleet's sweep on rented cards; the hive package, Ubuntu 24.04)",
|
||
"by": "measured by the fleet",
|
||
"note": ". Watts are class v3 (read 8 October 2026, 11:4x UK): the fleet's bench pack was the class v3 program (program_class v3, generator 3, load_class mx8-erad810f22d), so this row's watts and MH per watt are class v3 figures; the rate holds under class v4 (memory-bound: a 5070 Ti measured 78.7 MH/s at 141 W on class v3 and 78.8 at 224 W on class v4). The class v4 watts rerun on the same models lands with its date, the v3 watts kept beside as the shadow premium per card",
|
||
"v4_cost": "not measured (class v4 program only)",
|
||
"tuned": "stock, bench only (rented, not tuned)",
|
||
"driver_os": "NVIDIA driver 580, Ubuntu 24.04",
|
||
"hive": {
|
||
"core_mhz": null,
|
||
"mem_mhz": null,
|
||
"pl_w": null,
|
||
"label": "stock (no measured tune point; the 5080 and 9070 XT passes and the class v4 efficiency pass land theirs when read)"
|
||
},
|
||
"group": "buy",
|
||
"watts_class": "v3",
|
||
"watts_display": "102.8 (class v3)"
|
||
},
|
||
{
|
||
"card": "NVIDIA RTX 5070 Ti (16 GB)",
|
||
"generator": "v2",
|
||
"mh_s": 78.43,
|
||
"watts": 145.6,
|
||
"mh_per_w": 0.539,
|
||
"miner": "the hive package igneum-worker-cuda, class v4 program",
|
||
"date": "2026-10-07",
|
||
"source": "bench log: 7 October 2026, every rentable card on the hash (the fleet's sweep on rented cards; the hive package, Ubuntu 24.04)",
|
||
"by": "measured by the fleet",
|
||
"note": ". Watts are class v3 (read 8 October 2026, 11:4x UK): the fleet's bench pack was the class v3 program (program_class v3, generator 3, load_class mx8-erad810f22d), so this row's watts and MH per watt are class v3 figures; the rate holds under class v4 (memory-bound: a 5070 Ti measured 78.7 MH/s at 141 W on class v3 and 78.8 at 224 W on class v4). The class v4 watts rerun on the same models lands with its date, the v3 watts kept beside as the shadow premium per card",
|
||
"v4_cost": "not measured (class v4 program only)",
|
||
"tuned": "stock, bench only (rented, not tuned)",
|
||
"driver_os": "NVIDIA driver 580, Ubuntu 24.04",
|
||
"hive": {
|
||
"core_mhz": null,
|
||
"mem_mhz": null,
|
||
"pl_w": null,
|
||
"label": "stock (no measured tune point; the 5080 and 9070 XT passes and the class v4 efficiency pass land theirs when read)"
|
||
},
|
||
"group": "buy",
|
||
"watts_class": "v3",
|
||
"watts_display": "145.6 (class v3)"
|
||
},
|
||
{
|
||
"card": "NVIDIA RTX A5000 (24 GB)",
|
||
"generator": "v2",
|
||
"mh_s": 47.64,
|
||
"watts": null,
|
||
"mh_per_w": null,
|
||
"miner": "the hive package igneum-miner, class v4 program",
|
||
"date": "2026-10-07",
|
||
"source": "the fleet's standing voter (status line, 7 October 2026)",
|
||
"by": "reported by the fleet",
|
||
"note": "a standing voter's status line, 18:00Z; watts not read",
|
||
"v4_cost": "not measured (class v4 program only)",
|
||
"tuned": "stock, mining",
|
||
"driver_os": "NVIDIA driver, Ubuntu 24.04",
|
||
"hive": {
|
||
"core_mhz": null,
|
||
"mem_mhz": null,
|
||
"pl_w": null,
|
||
"label": "stock (no measured tune point; the 5080 and 9070 XT passes and the class v4 efficiency pass land theirs when read)"
|
||
},
|
||
"group": "datacentre"
|
||
},
|
||
{
|
||
"card": "NVIDIA L40S (48 GB)",
|
||
"generator": "v2",
|
||
"mh_s": 56.36,
|
||
"watts": 240.7,
|
||
"mh_per_w": 0.234,
|
||
"miner": "the hive package igneum-worker-cuda, class v4 program",
|
||
"date": "2026-10-07",
|
||
"source": "bench log: 7 October 2026, every rentable card on the hash (the fleet's sweep on rented cards; the hive package, Ubuntu 24.04)",
|
||
"by": "measured by the fleet",
|
||
"note": ". Watts are class v3 (read 8 October 2026, 11:4x UK): the fleet's bench pack was the class v3 program (program_class v3, generator 3, load_class mx8-erad810f22d), so this row's watts and MH per watt are class v3 figures; the rate holds under class v4 (memory-bound: a 5070 Ti measured 78.7 MH/s at 141 W on class v3 and 78.8 at 224 W on class v4). The class v4 watts rerun on the same models lands with its date, the v3 watts kept beside as the shadow premium per card",
|
||
"v4_cost": "not measured (class v4 program only)",
|
||
"tuned": "stock, bench only (rented, not tuned)",
|
||
"driver_os": "NVIDIA driver 580, Ubuntu 24.04",
|
||
"hive": {
|
||
"core_mhz": null,
|
||
"mem_mhz": null,
|
||
"pl_w": null,
|
||
"label": "stock (no measured tune point; the 5080 and 9070 XT passes and the class v4 efficiency pass land theirs when read)"
|
||
},
|
||
"group": "datacentre",
|
||
"watts_class": "v3",
|
||
"watts_display": "240.7 (class v3)"
|
||
},
|
||
{
|
||
"card": "NVIDIA A100 PCIe (80 GB)",
|
||
"generator": "v2",
|
||
"mh_s": 154.97,
|
||
"watts": 299.6,
|
||
"mh_per_w": 0.517,
|
||
"miner": "the hive package igneum-worker-cuda, class v4 program",
|
||
"date": "2026-10-07",
|
||
"source": "bench log: 7 October 2026, every rentable card on the hash (the fleet's sweep on rented cards; the hive package, Ubuntu 24.04)",
|
||
"by": "measured by the fleet",
|
||
"note": ". Watts are class v3 (read 8 October 2026, 11:4x UK): the fleet's bench pack was the class v3 program (program_class v3, generator 3, load_class mx8-erad810f22d), so this row's watts and MH per watt are class v3 figures; the rate holds under class v4 (memory-bound: a 5070 Ti measured 78.7 MH/s at 141 W on class v3 and 78.8 at 224 W on class v4). The class v4 watts rerun on the same models lands with its date, the v3 watts kept beside as the shadow premium per card",
|
||
"v4_cost": "not measured (class v4 program only)",
|
||
"tuned": "stock, bench only (rented, not tuned)",
|
||
"driver_os": "NVIDIA driver 580, Ubuntu 24.04",
|
||
"hive": {
|
||
"core_mhz": null,
|
||
"mem_mhz": null,
|
||
"pl_w": null,
|
||
"label": "stock (no measured tune point; the 5080 and 9070 XT passes and the class v4 efficiency pass land theirs when read)"
|
||
},
|
||
"group": "datacentre",
|
||
"watts_class": "v3",
|
||
"watts_display": "299.6 (class v3)"
|
||
},
|
||
{
|
||
"card": "NVIDIA A100 SXM (80 GB)",
|
||
"generator": "v2",
|
||
"mh_s": 138.39,
|
||
"watts": 266.3,
|
||
"mh_per_w": 0.52,
|
||
"miner": "the hive package igneum-worker-cuda, class v4 program",
|
||
"date": "2026-10-07",
|
||
"source": "bench log: 7 October 2026, every rentable card on the hash (the fleet's sweep on rented cards; the hive package, Ubuntu 24.04)",
|
||
"by": "measured by the fleet",
|
||
"note": ". Watts are class v3 (read 8 October 2026, 11:4x UK): the fleet's bench pack was the class v3 program (program_class v3, generator 3, load_class mx8-erad810f22d), so this row's watts and MH per watt are class v3 figures; the rate holds under class v4 (memory-bound: a 5070 Ti measured 78.7 MH/s at 141 W on class v3 and 78.8 at 224 W on class v4). The class v4 watts rerun on the same models lands with its date, the v3 watts kept beside as the shadow premium per card",
|
||
"v4_cost": "not measured (class v4 program only)",
|
||
"tuned": "stock, bench only (rented, not tuned)",
|
||
"driver_os": "NVIDIA driver 580, Ubuntu 24.04",
|
||
"hive": {
|
||
"core_mhz": null,
|
||
"mem_mhz": null,
|
||
"pl_w": null,
|
||
"label": "stock (no measured tune point; the 5080 and 9070 XT passes and the class v4 efficiency pass land theirs when read)"
|
||
},
|
||
"group": "datacentre",
|
||
"watts_class": "v3",
|
||
"watts_display": "266.3 (class v3)"
|
||
},
|
||
{
|
||
"card": "NVIDIA H200 SXM (141 GB)",
|
||
"generator": "v2",
|
||
"mh_s": 313.04,
|
||
"watts": 432.9,
|
||
"mh_per_w": 0.723,
|
||
"miner": "the hive package igneum-worker-cuda, class v4 program",
|
||
"date": "2026-10-07",
|
||
"source": "bench log: 7 October 2026, every rentable card on the hash (the fleet's sweep on rented cards; the hive package, Ubuntu 24.04)",
|
||
"by": "measured by the fleet",
|
||
"note": ". Watts are class v3 (read 8 October 2026, 11:4x UK): the fleet's bench pack was the class v3 program (program_class v3, generator 3, load_class mx8-erad810f22d), so this row's watts and MH per watt are class v3 figures; the rate holds under class v4 (memory-bound: a 5070 Ti measured 78.7 MH/s at 141 W on class v3 and 78.8 at 224 W on class v4). The class v4 watts rerun on the same models lands with its date, the v3 watts kept beside as the shadow premium per card",
|
||
"v4_cost": "not measured (class v4 program only)",
|
||
"tuned": "stock, bench only (rented, not tuned)",
|
||
"driver_os": "NVIDIA driver 580, Ubuntu 24.04",
|
||
"hive": {
|
||
"core_mhz": null,
|
||
"mem_mhz": null,
|
||
"pl_w": null,
|
||
"label": "stock (no measured tune point; the 5080 and 9070 XT passes and the class v4 efficiency pass land theirs when read)"
|
||
},
|
||
"group": "datacentre",
|
||
"watts_class": "v3",
|
||
"watts_display": "432.9 (class v3)"
|
||
},
|
||
{
|
||
"card": "NVIDIA B200 (180 GB)",
|
||
"generator": "v2",
|
||
"mh_s": 416.35,
|
||
"watts": 855.6,
|
||
"mh_per_w": 0.487,
|
||
"miner": "the hive package igneum-worker-cuda, class v4 program",
|
||
"date": "2026-10-07",
|
||
"source": "bench log: 7 October 2026, every rentable card on the hash (the fleet's sweep on rented cards; the hive package, Ubuntu 24.04)",
|
||
"by": "measured by the fleet",
|
||
"note": ". Watts are class v3 (read 8 October 2026, 11:4x UK): the fleet's bench pack was the class v3 program (program_class v3, generator 3, load_class mx8-erad810f22d), so this row's watts and MH per watt are class v3 figures; the rate holds under class v4 (memory-bound: a 5070 Ti measured 78.7 MH/s at 141 W on class v3 and 78.8 at 224 W on class v4). The class v4 watts rerun on the same models lands with its date, the v3 watts kept beside as the shadow premium per card",
|
||
"v4_cost": "not measured (class v4 program only)",
|
||
"tuned": "stock, bench only (rented, not tuned)",
|
||
"driver_os": "NVIDIA driver 580, Ubuntu 24.04",
|
||
"hive": {
|
||
"core_mhz": null,
|
||
"mem_mhz": null,
|
||
"pl_w": null,
|
||
"label": "stock (no measured tune point; the 5080 and 9070 XT passes and the class v4 efficiency pass land theirs when read)"
|
||
},
|
||
"group": "datacentre",
|
||
"watts_class": "v3",
|
||
"watts_display": "855.6 (class v3)"
|
||
},
|
||
{
|
||
"card": "NVIDIA RTX PRO 6000 Blackwell (96 GB)",
|
||
"generator": "v2",
|
||
"mh_s": 130.49,
|
||
"watts": 288.7,
|
||
"mh_per_w": 0.452,
|
||
"miner": "the hive package igneum-worker-cuda, class v4 program",
|
||
"date": "2026-10-07",
|
||
"source": "bench log: 7 October 2026, every rentable card on the hash (the fleet's sweep on rented cards; the hive package, Ubuntu 24.04)",
|
||
"by": "measured by the fleet",
|
||
"note": ". Watts are class v3 (read 8 October 2026, 11:4x UK): the fleet's bench pack was the class v3 program (program_class v3, generator 3, load_class mx8-erad810f22d), so this row's watts and MH per watt are class v3 figures; the rate holds under class v4 (memory-bound: a 5070 Ti measured 78.7 MH/s at 141 W on class v3 and 78.8 at 224 W on class v4). The class v4 watts rerun on the same models lands with its date, the v3 watts kept beside as the shadow premium per card",
|
||
"v4_cost": "not measured (class v4 program only)",
|
||
"tuned": "stock, bench only (rented, not tuned)",
|
||
"driver_os": "NVIDIA driver 580, Ubuntu 24.04",
|
||
"hive": {
|
||
"core_mhz": null,
|
||
"mem_mhz": null,
|
||
"pl_w": null,
|
||
"label": "stock (no measured tune point; the 5080 and 9070 XT passes and the class v4 efficiency pass land theirs when read)"
|
||
},
|
||
"group": "datacentre",
|
||
"watts_class": "v3",
|
||
"watts_display": "288.7 (class v3)"
|
||
},
|
||
{
|
||
"card": "NVIDIA RTX 5070 Ti (16 GB)",
|
||
"generator": "v2",
|
||
"mh_s": 78.45,
|
||
"mh_per_w": 0.322,
|
||
"watts": 214,
|
||
"miner": "bench pack, igneum-worker-cuda, class v4 program (3 x 300 dispatches of 2^22)",
|
||
"date": "2026-10-08",
|
||
"source": "model sweep 2026-10-08, row 1 (a rented card, result cb2-rtx-5070-ti-16-gb-7324-result.json; 09:23Z); the class v4 watts rerun, 8 October 2026 (result cb4-rtx-5070-ti-16-gb-1858-result.json, the v4-devnet-epoch0 pack, sub-version 3, three runs of about 30 s, the class v3 pack paired on the same host)",
|
||
"by": "measured by the fleet",
|
||
"note": "rented single-card host, 0.06 h; power.draw mean 135.9 W (instant 139.0, max 140.0, limit 300 W), SM 2,795 MHz mean, memory 13,801 MHz, 47 C, no throttle reason; self-test PASS (96 of 96 vector lanes); the class v5 kit holds the same rate on this card (78.72 MH/s, fingerprint matched); read ceiling 79.6 MH/s, so the hash runs at 0.99 of it. Class v4 watts (8 October 2026, the rerun, self-test PASS): 214 W at 68.94 MH/s, 0.322 MH per watt; the class v3 pack on the same host read 140.2 W at the same rate, so the shadow premium on this card is +52.6 percent of watts for no rate. two 5070 Ti memory populations exist: this board and one 7 October board read 69 MH/s, three others 78.4 to 78.8, all reporting the same 13,801 MHz memory clock, so the rate reads as a range with the host; the grid lane's own pair on a 78 MH/s board (141 W class v3, 224 W class v4, +59 percent) agrees on the watts to 10 W and gives 0.350 MH per watt there",
|
||
"v4_cost": "not measured (class v4 program only)",
|
||
"tuned": "stock, bench only (rented, no clock control on the host)",
|
||
"driver_os": "NVIDIA driver 595.84, Ubuntu 24.04 (CUDA 12.8.1 image)",
|
||
"hive": {
|
||
"core_mhz": null,
|
||
"mem_mhz": null,
|
||
"pl_w": null,
|
||
"label": "stock (rented card, no clock control on the host; no measured tune point)"
|
||
},
|
||
"group": "buy",
|
||
"watts_display": "214 (class v4)",
|
||
"mh_s_display": "69 to 78 by board (68.94 on this host)"
|
||
},
|
||
{
|
||
"generator": "v2",
|
||
"miner": "bench pack, igneum-worker-cuda, class v4 program (3 x 300 dispatches of 2^22)",
|
||
"date": "2026-10-08",
|
||
"by": "measured by the fleet",
|
||
"v4_cost": "not measured (class v4 program only)",
|
||
"tuned": "stock, bench only (rented, no clock control on the host)",
|
||
"hive": {
|
||
"core_mhz": null,
|
||
"mem_mhz": null,
|
||
"pl_w": null,
|
||
"label": "stock (rented card, no clock control on the host; no measured tune point)"
|
||
},
|
||
"group": "buy",
|
||
"card": "NVIDIA RTX 4070 Ti Super (16 GB)",
|
||
"mh_s": 41.24,
|
||
"watts": 137.8,
|
||
"mh_per_w": 0.268,
|
||
"driver_os": "NVIDIA driver 615.71.09, Ubuntu 24.04 (CUDA 12.8.1 image)",
|
||
"source": "model sweep 2026-10-08, row 2 (a rented card, result cb2-rtx-4070-ti-super-7325-result.json; 09:26Z); the class v4 watts rerun, 8 October 2026 (result cb4-rtx-4070-ti-super-5733-result.json, the v4-devnet-epoch0 pack, sub-version 3, three runs of about 30 s, the class v3 pack paired on the same host)",
|
||
"note": "rented single-card host, 0.10 h; power.draw mean 142.6 W (max 145.2, limit 285 W), SM 2,885 MHz mean, memory 10,251 MHz, 47 C, the SW thermal bit set with no rate effect (three runs within 0.02 percent); self-test PASS (96 of 96 vector lanes); the class v5 kit holds the rate (41.37 MH/s, fingerprint matched); read ceiling 41.6 MH/s, the hash at 0.99 of it. The Ada 192-bit bus class: the same MH per watt as the 4070 Ti; the extra 4 GB buys headroom, not rate. Class v4 watts (8 October 2026, the rerun on the frozen v4-devnet-epoch0 pack, self-test PASS): 137.8 W at 36.93 MH/s, 0.268 MH per watt; the class v3 pack on the same host read 102.3 W at the same rate, so the shadow premium on this card is +34.7 percent of watts for no rate (the class is memory-bound). this host is a 210 W, 2,400 MHz board at 36.9 MH/s on both classes against the morning board's 41.2, so the rate reads as a range with the host noted; the premium is smaller than the 5070's because this board sits nearer its cap",
|
||
"watts_display": "137.8 (class v4)",
|
||
"mh_s_display": "37 to 41 by board (36.93 on this host)"
|
||
},
|
||
{
|
||
"generator": "v2",
|
||
"miner": "bench pack, igneum-worker-cuda, class v4 program (3 x 300 dispatches of 2^22)",
|
||
"date": "2026-10-08",
|
||
"by": "measured by the fleet",
|
||
"v4_cost": "not measured (class v4 program only)",
|
||
"tuned": "stock, bench only (rented, no clock control on the host)",
|
||
"hive": {
|
||
"core_mhz": null,
|
||
"mem_mhz": null,
|
||
"pl_w": null,
|
||
"label": "stock (rented card, no clock control on the host; no measured tune point)"
|
||
},
|
||
"group": "buy",
|
||
"card": "NVIDIA RTX 3080 Ti (12 GB)",
|
||
"mh_s": 58.86,
|
||
"watts": 293.5,
|
||
"mh_per_w": 0.201,
|
||
"driver_os": "NVIDIA driver 580.65.06, Ubuntu 24.04 (CUDA 12.8.1 image)",
|
||
"source": "model sweep 2026-10-08, row 3 (a rented card, result cb2-rtx-3080-ti-12-gb-efll-result.json; 09:28Z)",
|
||
"note": "rented single-card host, 0.04 h; power.draw mean 293.5 W (max 299.6, limit 320 W), SM 1,936 MHz mean, memory 9,251 MHz, 74 C, the SW power-cap bit set 26 W under the limit; self-test PASS (96 of 96 vector lanes); the class v5 kit runs 2.5 percent faster on this card (60.38 MH/s, fingerprint matched); read ceiling 58.9 MH/s, the hash at 1.00 of it. Matches the 7 October row (58.95 MH/s) across hosts; the worst MH per watt of the sweep and the cheapest MH per rented hour, so a buyer on a power bill prefers the 5070 Ti and a renter this card. Class v4 pair (8 October 2026, result cb4-rtx-3080-ti-12-gb-7647-result.json, a different and deep-capped board: 220 W host cap on a 350 W card, the SM clock collapsed to 749 MHz): 42.24 MH/s mean at 216.2 W under class v4 against 44.93 MH/s at 166.2 W under class v3 on that board, the shadow premium +30.1 percent of watts and, on this cap, 5 percent of rate: the first cap that costs rate (a cap near 63 percent of stock on a 350 W GDDR6X card starves the SM clock the memory loop needs, where the 4070 Super at half its 220 W and the 3070 at 88 percent held full rate). The uncapped morning rate (58.86 MH/s) stands as this card's rate; its class v4 watts on an uncapped board are not yet measured and would read about 380 W by this pair's ratio (an estimate). The rule from the pairs so far: a power cap holds the rate until the SM clock falls below roughly 1.8 GHz on Ampere and 2.4 GHz on Ada",
|
||
"watts_class": "v3",
|
||
"watts_display": "293.5 (class v3, uncapped board)"
|
||
},
|
||
{
|
||
"generator": "v2",
|
||
"miner": "bench pack, igneum-worker-cuda, class v4 program (3 x 300 dispatches of 2^22)",
|
||
"date": "2026-10-08",
|
||
"by": "measured by the fleet",
|
||
"v4_cost": "not measured (class v4 program only)",
|
||
"tuned": "stock, bench only (rented, no clock control on the host)",
|
||
"hive": {
|
||
"core_mhz": null,
|
||
"mem_mhz": null,
|
||
"pl_w": null,
|
||
"label": "stock (rented card, no clock control on the host; no measured tune point)"
|
||
},
|
||
"group": "buy",
|
||
"card": "NVIDIA RTX 4080 (16 GB)",
|
||
"mh_s": 40.71,
|
||
"watts": 185.6,
|
||
"mh_per_w": 0.219,
|
||
"driver_os": "NVIDIA driver 595.84, Ubuntu 24.04 (CUDA 12.8.1 image)",
|
||
"source": "model sweep 2026-10-08, row 4 (a rented card, result cb2-rtx-4080-16-gb-7347-result.json; 09:28Z); the class v4 watts rerun, 8 October 2026 (result cb4-rtx-4080-16-gb-7107-result.json, the v4-devnet-epoch0 pack, sub-version 3, three runs of about 30 s, the class v3 pack paired on the same host)",
|
||
"note": "rented single-card host, 0.15 h; power.draw mean 128.6 W (max 130.5, limit 320 W), SM 2,776 MHz mean, memory 10,801 MHz, 38 C, no throttle reason; self-test PASS (96 of 96 vector lanes); the class v5 kit holds the rate (40.80 MH/s, fingerprint matched); read ceiling 41.0 MH/s, the hash at 0.99 of it. One percent under the 4070 Ti Super at 14 W less: the Ada 16 GB tier is a 41 MH/s tier whichever card. Class v4 watts (8 October 2026, the rerun on the frozen v4-devnet-epoch0 pack, self-test PASS): 185.6 W at 40.73 MH/s, 0.219 MH per watt; the class v3 pack on the same host read 128.1 W at the same rate, so the shadow premium on this card is +44.9 percent of watts for no rate (the class is memory-bound). the same board as the morning row (offer 54551253; the v3 draw repeats to half a watt); the 256-bit board's premium sits above the 192-bit cards' third",
|
||
"watts_display": "185.6 (class v4)"
|
||
},
|
||
{
|
||
"generator": "v2",
|
||
"miner": "bench pack, igneum-worker-cuda, class v4 program (3 x 300 dispatches of 2^22)",
|
||
"date": "2026-10-08",
|
||
"by": "measured by the fleet",
|
||
"v4_cost": "not measured (class v4 program only)",
|
||
"tuned": "stock, bench only (rented, no clock control on the host)",
|
||
"group": "buy",
|
||
"card": "NVIDIA RTX 3070 (8 GB)",
|
||
"mh_s": 37.09,
|
||
"watts": 196.4,
|
||
"mh_per_w": 0.189,
|
||
"driver_os": "NVIDIA driver 580.65.06, Ubuntu 24.04 (CUDA 12.8.1 image)",
|
||
"source": "model sweep 2026-10-08, row 5 (a rented card, result cb2-rtx-3070-8-gb-qh9j-result.json; 09:32Z); the class v4 watts rerun, 8 October 2026 (result cb4-rtx-3070-8-gb-l6mu-result.json, the v4-devnet-epoch0 pack, sub-version 3, three runs of about 30 s, the class v3 pack paired on the same host)",
|
||
"note": "rented single-card host, 0.06 h; power.draw mean 142.3 W (max 146.7, limit 225 W), SM 2,002 MHz mean, memory 6,801 MHz, 57 C, no throttle reason; self-test PASS (96 of 96 vector lanes); the class v5 kit holds the rate (37.14 MH/s, fingerprint matched); read ceiling 37.2 MH/s, the hash at 1.00 of it. Against the 3070 Ti: 5 percent less rate for 25 percent less power, the better owner card of the two; 8 GB holds the class v4 set with room. Class v4 watts (8 October 2026, the rerun, self-test PASS): 196.4 W at 37.11 MH/s, 0.189 MH per watt; the class v3 pack on the same host read 153.4 W at the same rate, so the shadow premium on this card is +28 percent of watts for no rate. this board is capped at 193 W by the host (stock 220) and the class v4 draw sits on the cap with the power-cap bit set while the rate holds, the same shape as the capped 4070 Super; the first Ampere pair",
|
||
"hive": {
|
||
"core_mhz": null,
|
||
"mem_mhz": null,
|
||
"pl_w": null,
|
||
"label": "stock (rented card, no clock control on the host; no measured tune point)"
|
||
},
|
||
"watts_display": "196.4 (class v4)"
|
||
},
|
||
{
|
||
"generator": "v2",
|
||
"miner": "bench pack, igneum-worker-cuda, class v4 program (3 x 300 dispatches of 2^22)",
|
||
"date": "2026-10-08",
|
||
"by": "measured by the fleet",
|
||
"v4_cost": "not measured (class v4 program only)",
|
||
"tuned": "stock, bench only (rented, no clock control on the host)",
|
||
"group": "buy",
|
||
"card": "NVIDIA RTX 3070 Ti (8 GB)",
|
||
"mh_s": 38.98,
|
||
"watts": 267.6,
|
||
"mh_per_w": 0.146,
|
||
"driver_os": "NVIDIA driver 595.71.05, Ubuntu 24.04 (CUDA 12.8.1 image)",
|
||
"source": "model sweep 2026-10-08, row 6 (a rented card, result cb2-rtx-3070-ti-8-gb-8528-result.json; 09:33Z); the class v4 watts rerun, 8 October 2026 (result cb4-rtx-3070-ti-8-gb-7705-result.json, the v4-devnet-epoch0 pack, sub-version 3, three runs of about 30 s, the class v3 pack paired on the same host)",
|
||
"note": "rented single-card host, 0.07 h; power.draw mean 177.1 W (max 183.6, limit 290 W), SM 1,955 MHz mean, memory 9,251 MHz, 67 C, no throttle reason; self-test PASS (96 of 96 vector lanes); the class v5 kit holds the rate (39.12 MH/s, fingerprint matched); read ceiling 39.1 MH/s, the hash at 1.00 of it. Repeats the 7 October row on another host (38.98 then, 38.98 now; 178 then 177 W), so the class v4 number is host-independent to 0.1 percent. Class v4 watts (8 October 2026, the rerun, self-test PASS): 267.6 W at 39.1 MH/s, 0.146 MH per watt; the class v3 pack on the same host read 180.4 W at the same rate, so the shadow premium on this card is +48.3 percent of watts for no rate. the same board as the 7 October row (offer 36538839), uncapped (a 310 W AIB); the uncapped GDDR6X Ampere premium sits with the 4080's and the 5070's rather than the 192-bit Ada third, so the premium scales with the SM the board had idle under class v3",
|
||
"hive": {
|
||
"core_mhz": null,
|
||
"mem_mhz": null,
|
||
"pl_w": null,
|
||
"label": "stock (rented card, no clock control on the host; no measured tune point)"
|
||
},
|
||
"watts_display": "267.6 (class v4)"
|
||
},
|
||
{
|
||
"generator": "v2",
|
||
"miner": "bench pack, igneum-worker-cuda, class v4 program (3 x 300 dispatches of 2^22)",
|
||
"date": "2026-10-08",
|
||
"by": "measured by the fleet",
|
||
"v4_cost": "not measured (class v4 program only)",
|
||
"tuned": "stock, bench only (rented, no clock control on the host)",
|
||
"group": "buy",
|
||
"card": "NVIDIA RTX 4060 Ti (16 GB)",
|
||
"mh_s": 20.07,
|
||
"watts": 102.3,
|
||
"mh_per_w": 0.196,
|
||
"driver_os": "NVIDIA driver 595.71.05, Ubuntu 24.04 (CUDA 12.8.1 image)",
|
||
"source": "model sweep 2026-10-08, row 7 (a rented card, result cb2-rtx-4060-ti-16-gb-7364-result.json; 09:33Z); the class v4 watts rerun, 8 October 2026 (result cb4-rtx-4060-ti-16-gb-6679-result.json, the v4-devnet-epoch0 pack, sub-version 3, three runs of about 30 s, the class v3 pack paired on the same host)",
|
||
"note": "rented single-card host, 0.22 h; power.draw mean 79.2 W (max 86.2, limit 165 W), SM 2,836 MHz mean, memory 8,751 MHz, 63 C, no throttle reason; self-test PASS (96 of 96 vector lanes); the class v5 kit holds the rate (20.10 MH/s, fingerprint matched). Repeats the 7 October number (20.10 then, 20.07 now); the one card of the sweep well under its probed read ceiling (0.65 of 30.9 MH/s: the 128-bit bus with the large L2 makes the chase probe optimistic), so 20 MH/s at 79 W is the card's rate; 16 GB holds any class with room. Class v4 watts (8 October 2026, the rerun on the frozen v4-devnet-epoch0 pack, self-test PASS): 102.3 W at 20.1 MH/s, 0.196 MH per watt; the class v3 pack on the same host read 76.6 W at the same rate, so the shadow premium on this card is +33.6 percent of watts for no rate (the class is memory-bound). the same board as the 7 October row (offer 47543124); the rate is the same on every 4060 Ti host and both classes (20.07 to 20.10)",
|
||
"hive": {
|
||
"core_mhz": null,
|
||
"mem_mhz": null,
|
||
"pl_w": null,
|
||
"label": "stock (rented card, no clock control on the host; no measured tune point)"
|
||
},
|
||
"watts_display": "102.3 (class v4)"
|
||
},
|
||
{
|
||
"generator": "v2",
|
||
"miner": "bench pack, igneum-worker-cuda, class v4 program (3 x 300 dispatches of 2^22)",
|
||
"date": "2026-10-08",
|
||
"by": "measured by the fleet",
|
||
"v4_cost": "not measured (class v4 program only)",
|
||
"tuned": "stock, bench only (rented, no clock control on the host)",
|
||
"group": "buy",
|
||
"card": "NVIDIA RTX 5070 (12 GB)",
|
||
"mh_s": 51.81,
|
||
"watts": 176.1,
|
||
"mh_per_w": 0.334,
|
||
"driver_os": "NVIDIA driver 580.173.02, Ubuntu 24.04 (CUDA 12.8.1 image)",
|
||
"source": "model sweep 2026-10-08, row 8 (a rented card, result cb2-rtx-5070-12-gb-8750-result.json; 09:35Z); the class v4 watts rerun, 8 October 2026 (result cb4-rtx-5070-12-gb-5732-result.json, the v4-devnet-epoch0 pack, sub-version 3, three runs of about 30 s, the class v3 pack paired on the same host)",
|
||
"note": "rented single-card host, 0.09 h; power.draw mean 110.8 W (max 112.0, limit 250 W), SM 2,851 MHz mean, memory 13,801 MHz, 60 C, no throttle reason; self-test PASS (96 of 96 vector lanes); the class v5 kit holds the rate (51.98 MH/s, fingerprint matched); read ceiling 52.3 MH/s, the hash at 0.99 of it. Repeats the 7 October row (52.01 then, 51.82 now) at 8 W more on this host; second to the 5070 Ti in MH per watt among consumer cards (GDDR7 lifts Blackwell here, not SM count); 12 GB holds the class v4 set with 10 GB spare. Class v4 watts (8 October 2026, the rerun on the frozen v4-devnet-epoch0 pack, self-test PASS): 176.1 W at 58.89 MH/s, 0.334 MH per watt; the class v3 pack on the same host read 113.1 W at the same rate, so the shadow premium on this card is +55.7 percent of watts for no rate (the class is memory-bound). board-to-board spread: this host 58.9 MH/s on both classes, the morning host 51.8 (GDDR7 memory clocks differ by board), so the rate reads as a range with the host noted",
|
||
"hive": {
|
||
"core_mhz": null,
|
||
"mem_mhz": null,
|
||
"pl_w": null,
|
||
"label": "stock (rented card, no clock control on the host; no measured tune point)"
|
||
},
|
||
"watts_display": "176.1 (class v4)",
|
||
"mh_s_display": "52 to 59 by board (58.89 on this host)"
|
||
},
|
||
{
|
||
"generator": "v2",
|
||
"miner": "bench pack, igneum-worker-cuda, class v4 program (3 x 300 dispatches of 2^22)",
|
||
"date": "2026-10-08",
|
||
"by": "measured by the fleet",
|
||
"v4_cost": "not measured (class v4 program only)",
|
||
"tuned": "stock, bench only (rented, no clock control on the host)",
|
||
"group": "buy",
|
||
"card": "NVIDIA RTX 4070 Super (12 GB)",
|
||
"mh_s": 31.24,
|
||
"watts": 108.4,
|
||
"mh_per_w": 0.288,
|
||
"driver_os": "NVIDIA driver 580.178.04, Ubuntu 24.04 (CUDA 12.8.1 image)",
|
||
"source": "model sweep 2026-10-08, row 9 (a rented card, result cb2-rtx-4070-super-12--8582-result.json; 09:36Z); the class v4 watts rerun, 8 October 2026 (result cb4-rtx-4070-super-12--6238-result.json, the v4-devnet-epoch0 pack, sub-version 3, three runs of about 30 s, the class v3 pack paired on the same host)",
|
||
"note": "rented single-card host, 0.13 h; power.draw mean 100.2 W (max 103.9) under a 110 W host cap (stock 220 W), SM 2,764 MHz mean, memory 10,251 MHz, 53 C, no throttle reason; self-test PASS (96 of 96 vector lanes); the class v5 kit holds the rate (31.29 MH/s, fingerprint matched); read ceiling 34.4 MH/s, the hash at 0.91 of it. Lands on the 4070 Ti's number (31.26 on 7 October) at 7 W less (the same 192-bit 21 Gbps bus); the host's 110 W cap cost no rate, a tune-down reading in itself: an owner can cap a 4070 Super at half its stock power and lose nothing on class v4. Class v4 watts (8 October 2026, the rerun on the frozen v4-devnet-epoch0 pack, self-test PASS): 108.4 W at 31.25 MH/s, 0.288 MH per watt; the class v3 pack on the same host read 99.2 W at the same rate, so the shadow premium on this card is +9.3 percent of watts for no rate (the class is memory-bound). the same board as the morning row (host offer 51485188), capped at 110 W by the host (stock 220) with the SW power-cap bit set the whole run: the cap absorbs the class v4 stage's extra draw (the SM clock drops 10 percent, the rate does not move), so the premium is 9 percent here against a third on uncapped Ada boards; a power cap near half stock costs a 192-bit Ada card nothing on class v4",
|
||
"hive": {
|
||
"core_mhz": null,
|
||
"mem_mhz": null,
|
||
"pl_w": null,
|
||
"label": "stock (rented card, no clock control on the host; no measured tune point)"
|
||
},
|
||
"watts_display": "108.4 (class v4)"
|
||
},
|
||
{
|
||
"generator": "v2",
|
||
"miner": "bench pack, igneum-worker-cuda, class v4 program (3 x 300 dispatches of 2^22)",
|
||
"date": "2026-10-08",
|
||
"by": "measured by the fleet",
|
||
"v4_cost": "not measured (class v4 program only)",
|
||
"tuned": "stock, bench only (rented, no clock control on the host)",
|
||
"group": "buy",
|
||
"card": "NVIDIA RTX 3060 Ti (8 GB)",
|
||
"mh_s": 31.7,
|
||
"watts": 128.7,
|
||
"mh_per_w": 0.256,
|
||
"driver_os": "NVIDIA driver 595.91.07, Ubuntu 24.04 (CUDA 12.8.1 image)",
|
||
"source": "model sweep 2026-10-08, row 10 (a rented card, result cb2-rtx-3060-ti-8-gb-8771-result.json; 09:37Z); the class v4 watts rerun, 8 October 2026 (result cb4-rtx-3060-ti-8-gb-8620-result.json, the v4-devnet-epoch0 pack, sub-version 3, three runs of about 30 s, the class v3 pack paired on the same host)",
|
||
"note": "rented single-card host, 0.12 h; power.draw mean 100.4 W (max 104.7, limit 180 W), SM 1,560 MHz mean, memory 5,001 MHz on this host (below the 7,000 MHz GDDR6 stock), 61 C, no throttle reason; self-test PASS (96 of 96 vector lanes); the class v5 kit holds the rate (31.75 MH/s, fingerprint matched); read ceiling 31.8 MH/s, the hash at 1.00 of it. Four percent under the 7 October 3060 Ti row (33.1 on another host), consistent with this host's lower memory clock; the best MH per watt of the Ampere cards. Class v4 watts (8 October 2026, the rerun, self-test PASS): 128.7 W at 32.92 MH/s, 0.256 MH per watt; the class v3 pack on the same host read 129.9 W at the same rate, so the shadow premium on this card is -0.9 percent of watts for no rate. the cleanest cap reading of the set: this board is capped at 130 W by the host (stock 200) and both classes sit on the cap, the SM giving a quarter of its clock (1,722 to 1,297 MHz) while the rate holds, so a 3060 Ti at 65 percent of stock runs class v4 at full rate with no premium; the rate on this board (33.1) matches the 7 October host and sits 4 percent over the morning's slow-memory board, so the rate reads as a range",
|
||
"hive": {
|
||
"core_mhz": null,
|
||
"mem_mhz": null,
|
||
"pl_w": null,
|
||
"label": "stock (rented card, no clock control on the host; no measured tune point)"
|
||
},
|
||
"watts_display": "128.7 (class v4)",
|
||
"mh_s_display": "32 to 33 by board (33.06 on this host)"
|
||
},
|
||
{
|
||
"generator": "v2",
|
||
"miner": "bench pack, igneum-worker-cuda, class v4 program (3 x 300 dispatches of 2^22)",
|
||
"date": "2026-10-08",
|
||
"by": "measured by the fleet",
|
||
"v4_cost": "not measured (class v4 program only)",
|
||
"tuned": "stock, bench only (rented, no clock control on the host)",
|
||
"card": "NVIDIA RTX 2080 Ti (11 GB)",
|
||
"group": "buy",
|
||
"mh_s": 26.01,
|
||
"watts": 161.1,
|
||
"mh_per_w": 0.174,
|
||
"driver_os": "NVIDIA driver 580.159.03, Ubuntu 24.04 (CUDA 12.8.1 image)",
|
||
"source": "model sweep 2026-10-08, row 11 (a rented card, result cb2-rtx-2080-ti-9077-result.json; 09:40Z); the class v4 watts rerun, 8 October 2026 (result cb4-rtx-2080-ti-0387-result.json, a different board: 22 GB modded, the core held at 1,095 MHz, a 170 W cap; the class v3 pack paired on the same host)",
|
||
"note": "rented single-card host, 0.13 h; power.draw mean 224.6 W (max 234.7, limit 300 W; the driver reports no power average on Turing), SM 1,914 MHz mean, memory 6,802 MHz, 72 C, no throttle reason; self-test PASS (96 of 96 vector lanes); the class v5 kit holds the rate (26.04 MH/s, fingerprint matched); read ceiling 29.9 MH/s, the hash at 0.87 of it. The first Turing row: the 7 October 2080 Ti pod that left no result was a host fault, not the card. The worst MH per watt measured on any card (the Titan RTX, the same silicon, read 28.3 MH/s at 226 W on 7 October): an owner mines at a loss on any real power price; 11 GB holds the set. Class v4 watts (8 October 2026, the rerun, self-test PASS) on a tuned board (22 GB memory mod, the core held at 1,095 MHz by the host, a 170 W cap): 161.1 W at 28.05 MH/s, 0.174 MH per watt, the class v3 pack on the same host 139.2 W at 28.04, a premium of +15.7 percent for no rate; this tuned board runs 8 percent over the morning's stock 11 GB board (26.0 MH/s at 1,914 MHz and 224.6 W class v3), so the 2080 Ti's rate is set by its memory and a core lock near 1.1 GHz with a 170 W cap is the way to run one; the morning's stock board under class v4 would read about 0.09 MH per watt by the 2070 Super's premium (an inference)",
|
||
"hive": {
|
||
"core_mhz": null,
|
||
"mem_mhz": null,
|
||
"pl_w": null,
|
||
"label": "stock (rented card, no clock control on the host; no measured tune point)"
|
||
},
|
||
"watts_display": "161.1 (class v4, a tuned board)",
|
||
"mh_s_display": "26 to 28 by board (28.05 tuned on this host)"
|
||
},
|
||
{
|
||
"generator": "v2",
|
||
"miner": "bench pack, igneum-worker-cuda, class v4 program (3 x 300 dispatches of 2^22)",
|
||
"date": "2026-10-08",
|
||
"by": "measured by the fleet",
|
||
"v4_cost": "not measured (class v4 program only)",
|
||
"tuned": "stock, bench only (rented, no clock control on the host)",
|
||
"card": "NVIDIA RTX 2070 Super (8 GB)",
|
||
"group": "buy",
|
||
"mh_s": 19.09,
|
||
"watts": 204.2,
|
||
"mh_per_w": 0.094,
|
||
"driver_os": "NVIDIA driver 575.57.08, Ubuntu 24.04 (CUDA 12.8.1 image)",
|
||
"source": "model sweep 2026-10-08, row 12 (a rented card, result cb2-rtx-2070-super-8-g-9129-result.json; 09:41Z); the class v4 watts rerun, 8 October 2026 (result cb4-rtx-2070-super-8-g-9125-result.json, the v4-devnet-epoch0 pack, sub-version 3, three runs of about 30 s, the class v3 pack paired on the same host)",
|
||
"note": "rented single-card host, 0.15 h; power.draw mean 166.0 W (max 167.8, limit 215 W; no power average on Turing), SM 1,955 MHz mean, memory 6,802 MHz, 64 C, no throttle reason; self-test PASS (96 of 96 vector lanes); the class v5 kit holds the rate (19.12 MH/s, fingerprint matched); read ceiling 30.1 MH/s, the hash at 0.63 of it: Turing does not overlap the independent reads the hash needs (its indep probe 2.45 G loads/s binds). The Turing per-watt floor: a 4060's rate at twice the power. Class v4 watts (8 October 2026, the rerun, self-test PASS): 204.2 W at 19.1 MH/s, 0.094 MH per watt; the class v3 pack on the same host read 165.9 W at the same rate, so the shadow premium on this card is +23.1 percent of watts for no rate. the same board as the morning row; the first Turing pair, the smallest premium of the uncapped boards because Turing's SMs were busy under class v3 already (0.63 of its read ceiling); a 2060-class rate at a 3080-class draw: an owner mines at a loss on any real power price",
|
||
"hive": {
|
||
"core_mhz": null,
|
||
"mem_mhz": null,
|
||
"pl_w": null,
|
||
"label": "stock (rented card, no clock control on the host; no measured tune point)"
|
||
},
|
||
"watts_display": "204.2 (class v4)"
|
||
},
|
||
{
|
||
"generator": "v2",
|
||
"miner": "bench pack, igneum-worker-cuda, class v4 program (3 x 300 dispatches of 2^22)",
|
||
"date": "2026-10-08",
|
||
"by": "measured by the fleet",
|
||
"v4_cost": "not measured (class v4 program only)",
|
||
"tuned": "stock, bench only (rented, no clock control on the host)",
|
||
"card": "NVIDIA A100 SXM4 (80 GB)",
|
||
"group": "datacentre",
|
||
"mh_s": 138.1,
|
||
"watts": 489.3,
|
||
"mh_per_w": 0.282,
|
||
"driver_os": "NVIDIA driver 595.71.05, Ubuntu 24.04 (CUDA 12.8.1 image)",
|
||
"source": "model sweep 2026-10-08, row 13 (a rented card, result cb2-a100-80-gb-j79g-result.json; 09:43Z); the class v4 watts rerun, 8 October 2026 (result cb4-a100-80-gb-mdfz-result.json, the v4-devnet-epoch0 pack, sub-version 3, three runs of about 30 s, the class v3 pack paired on the same host)",
|
||
"note": "rented single-card host, 0.04 h; power.draw mean 268.6 W (max 274.1, limit 400 W; no power average on this host), SM 1,410 MHz, HBM2e 1,593 MHz, 44 C, no throttle reason; self-test PASS (96 of 96 vector lanes); the class v5 kit reads 136.48 MH/s, 1.3 percent under class v4 (fingerprint matched), the first card where v5 is not level with v4; read ceiling 138.6 MH/s, the hash at 1.00 of it. Repeats the three 7 October readings (138.39, 138.74, 138.76) to 0.3 percent on a fourth host; datacentre-class per watt, a third of a 3080 Ti's MH per rented dollar. Class v4 watts (8 October 2026, the rerun, self-test PASS): 489.3 W at 138 MH/s, 0.282 MH per watt; the class v3 pack on the same host read 274.3 W at the same rate, so the shadow premium on this card is +78.4 percent of watts for no rate. the 500 W SKU (the morning's board was the 400 W SKU; the class v3 draw holds across both); the largest premium of the pairs so far: the 108 SMs sit nearly idle under class v3 and the shadow stage puts them all to work, the card touching its 500 W cap without losing rate; under the live class the A100 falls from datacentre-class per watt to the capped 4070 Super's level; on the 400 W SKU the cap would bind and the rate should hold by the Ampere rule (an inference until a 400 W board is paired)",
|
||
"hive": {
|
||
"core_mhz": null,
|
||
"mem_mhz": null,
|
||
"pl_w": null,
|
||
"label": "stock (rented card, no clock control on the host; no measured tune point)"
|
||
},
|
||
"watts_display": "489.3 (class v4)"
|
||
},
|
||
{
|
||
"generator": "v2",
|
||
"miner": "bench pack, igneum-worker-cuda, class v4 program (3 x 300 dispatches of 2^22)",
|
||
"date": "2026-10-08",
|
||
"by": "measured by the fleet",
|
||
"v4_cost": "not measured (class v4 program only)",
|
||
"tuned": "stock, bench only (rented, no clock control on the host)",
|
||
"card": "NVIDIA H100 SXM (80 GB HBM3)",
|
||
"group": "datacentre",
|
||
"mh_s": 248.3,
|
||
"watts": 695.1,
|
||
"mh_per_w": 0.36,
|
||
"driver_os": "NVIDIA driver 580.126.09, Ubuntu 24.04 (CUDA 12.8.1 image)",
|
||
"source": "model sweep 2026-10-08, row 14 (a rented card, result cb2-h100-80-gb-rs3d-result.json; 09:43Z); the class v4 watts rerun, 8 October 2026 (result cb4-h100-80-gb-sbwo-result.json, the v4-devnet-epoch0 pack, sub-version 3, three runs of about 30 s, the class v3 pack paired on the same host)",
|
||
"note": "rented single-card host, 0.03 h; power.draw mean 411.7 W (instant 434.1, the largest gap between the two fields in the sweep, 22 W; max 437.1, limit 700 W), SM 1,980 MHz, HBM3 2,619 MHz, 36 C, no throttle reason; self-test PASS (96 of 96 vector lanes); the class v5 kit reads 252.64 MH/s, 1.5 percent over class v4 (fingerprint matched); read ceiling 252.4 MH/s, the hash at 0.99 of it. Repeats the 7 October rows (248.70, 248.21) on a third host; the best per-watt figure of the sweep on power.draw (0.573 on the instant field) and the worst MH per rented dollar: an owner's card on cheap power, never a renter's. Class v4 watts (8 October 2026, the rerun, self-test PASS): 695.1 W at 250.02 MH/s, 0.36 MH per watt; the class v3 pack on the same host read 456.9 W at the same rate, so the shadow premium on this card is +52.1 percent of watts for no rate. this board draws 45 W more than the morning's under class v3 at 1 percent more rate; under class v4 the H100 sits on its 700 W cap (SM 1,774 MHz, down from 1,980) and holds the rate; still the worst MH per rented dollar",
|
||
"hive": {
|
||
"core_mhz": null,
|
||
"mem_mhz": null,
|
||
"pl_w": null,
|
||
"label": "stock (rented card, no clock control on the host; no measured tune point)"
|
||
},
|
||
"watts_display": "695.1 (class v4)"
|
||
},
|
||
{
|
||
"generator": "v2",
|
||
"miner": "bench pack, igneum-worker-cuda, class v4 program (3 x 300 dispatches of 2^22)",
|
||
"date": "2026-10-08",
|
||
"by": "measured by the fleet",
|
||
"v4_cost": "not measured (class v4 program only)",
|
||
"tuned": "stock, bench only (rented, no clock control on the host)",
|
||
"card": "NVIDIA RTX A4000 (16 GB)",
|
||
"group": "datacentre",
|
||
"mh_s": 31.41,
|
||
"watts": 135.2,
|
||
"mh_per_w": 0.232,
|
||
"driver_os": "NVIDIA driver 595.91.07, Ubuntu 24.04 (CUDA 12.8.1 image)",
|
||
"source": "model sweep 2026-10-08, row 15 (a rented card, result cb2-rtx-a4000-16-gb-9473-result.json; 09:45Z); the class v4 watts rerun, 8 October 2026 (result cb4-rtx-a4000-16-gb-0549-result.json, the v4-devnet-epoch0 pack, sub-version 3, three runs of about 30 s, the class v3 pack paired on the same host)",
|
||
"note": "rented single-card host, 0.16 h; power.draw mean 112.8 W on a host that caps the card at 114 W (stock 140 W; the SW power-cap bit set the whole run), SM 1,562 MHz mean, memory 6,501 MHz, 81 C; self-test PASS (96 of 96 vector lanes); read ceiling 31.6 MH/s, the hash at 0.99 of it. Class v4 repeats the 7 October row (31.45 then, 31.41 now) under the cap. The class v5 kit's reading on this capped host is held off the page until an uncapped A4000 confirms it. Class v4 watts (8 October 2026, the rerun, self-test PASS): 135.2 W at 31.36 MH/s, 0.232 MH per watt; the class v3 pack on the same host read 136.1 W at the same rate, so the shadow premium on this card is -0.7 percent of watts for no rate. a different board from the morning's 114 W-capped one, at its 140 W stock limit and hot (96 C, the thermal bit set under both classes): the A4000 is a capped card already under class v3 on every host, so under class v4 it draws the same 135 to 140 W and holds the full rate with the SM giving a quarter of its clock; the morning's class v5 reading on the 114 W board follows from the same cap. The best renter's card under the live class after the capped 3060 Ti",
|
||
"hive": {
|
||
"core_mhz": null,
|
||
"mem_mhz": null,
|
||
"pl_w": null,
|
||
"label": "stock (rented card, no clock control on the host; no measured tune point)"
|
||
},
|
||
"watts_display": "135.2 (class v4)"
|
||
},
|
||
{
|
||
"generator": "v2",
|
||
"miner": "bench pack, igneum-worker-cuda, class v4 program (3 x 300 dispatches of 2^22)",
|
||
"date": "2026-10-08",
|
||
"by": "measured by the fleet",
|
||
"v4_cost": "not measured (class v4 program only)",
|
||
"tuned": "stock, bench only (rented, no clock control on the host)",
|
||
"card": "NVIDIA RTX A6000 (48 GB)",
|
||
"group": "datacentre",
|
||
"mh_s": 53.64,
|
||
"watts": 295,
|
||
"mh_per_w": 0.182,
|
||
"driver_os": "NVIDIA driver 595.84, Ubuntu 24.04 (CUDA 12.8.1 image)",
|
||
"source": "model sweep 2026-10-08, row 16 (a rented card, result cb2-rtx-a6000-48-gb-9600-result.json; 09:46Z); the class v4 watts rerun, 8 October 2026 (result cb4-rtx-a6000-48-gb-1814-result.json, the v4-devnet-epoch0 pack, sub-version 3, three runs of about 30 s, the class v3 pack paired on the same host)",
|
||
"note": "rented single-card host, 0.15 h; power.draw mean 239.1 W (max 251.0, limit 300 W), SM 1,913 MHz mean, memory 7,601 MHz, 65 C, no throttle reason; self-test PASS (96 of 96 vector lanes); the class v5 kit holds the rate (53.82 MH/s, fingerprint matched), so on an uncapped sm_86 card v5 is level with v4 and the A4000's v5 reading narrows to its power cap; read ceiling 53.8 MH/s, the hash at 1.00 of it. Repeats the 7 October row (53.66 then, 53.64 now) at 43 W less on this host; a 3090-class rate at a 3090-class draw. Class v4 watts (8 October 2026, the rerun, self-test PASS): 295.0 W at 53.67 MH/s, 0.182 MH per watt; the class v3 pack on the same host read 253.9 W at the same rate (the board 9 C warmer than the morning, 15 W over its morning class v3 reading), so the shadow premium on this card is +16.2 percent of watts for no rate: the A6000 lands on its stock 300 W cap under class v4 and holds the rate, the fourth card to do so with the H100, the A100 and the A4000, so a stock cap reached under class v4 is a note, not a penalty. The rerun is complete: 22 class v4 watts rows on 22 models, every pod destroyed",
|
||
"hive": {
|
||
"core_mhz": null,
|
||
"mem_mhz": null,
|
||
"pl_w": null,
|
||
"label": "stock (rented card, no clock control on the host; no measured tune point)"
|
||
},
|
||
"watts_display": "295 (class v4)"
|
||
},
|
||
{
|
||
"generator": "v2",
|
||
"miner": "bench pack, igneum-worker-cuda, class v4 program (3 x 300 dispatches of 2^22)",
|
||
"date": "2026-10-08",
|
||
"by": "measured by the fleet",
|
||
"v4_cost": "not measured (class v4 program only)",
|
||
"tuned": "stock, bench only (rented; Pascal has no clock lock on any host)",
|
||
"card": "NVIDIA GTX 1080 Ti (11 GB)",
|
||
"group": "buy",
|
||
"mh_s": 16.26,
|
||
"watts": 202.7,
|
||
"mh_per_w": 0.08,
|
||
"driver_os": "NVIDIA driver 580.173.02, Ubuntu 24.04 (CUDA 12.8.1 image)",
|
||
"source": "model sweep 2026-10-08, rows 17 and 22 (two rented hosts, results cb2-gtx-1080-ti-11-gb-0377-result.json and cb2-gtx-1080-ti-11-gb-1452-result.json; 09:49Z and 10:02Z); the class v4 watts rerun, 8 October 2026 (result cb4-gtx-1080-ti-11-gb-9935-result.json, the v4-devnet-epoch0 pack, sub-version 3, three runs of about 30 s, the class v3 pack paired on the same host)",
|
||
"note": "the mean of the first host's two clean runs (16.26 MH/s at 124.3 W, the card uncapped at a 280 W limit); a second host read 16.29 MH/s at 129.4 W under a 130 W host cap with five of five self-tests passing, so the first host's one-in-three cache self-test failure was that host's VRAM and not Pascal, and the flag is cleared. Power.draw on the first host max 125.5 W (no power average on Pascal), SM 1,936 MHz mean, memory 5,005 MHz, 59 C; the class v5 kit held the rate on the uncapped host (16.27 MH/s) and read 13.27 MH/s on the 130 W-capped one (fingerprint matched on both); read ceiling 16.3 MH/s, the hash at 1.00 of it. The first Pascal row: a 2017 card that runs the class at its own ceiling. Class v4 watts (8 October 2026, the rerun, self-test PASS): 202.7 W at 16.29 MH/s, 0.08 MH per watt; the class v3 pack on the same host read 124.5 W at the same rate, so the shadow premium on this card is +62.8 percent of watts for no rate. an uncapped 280 W board (five of five self-tests PASS, so the first host's cache fault stays that host's); the largest premium of the pairs, pure added work (the SM clock did not move between classes): Pascal has no fast integer path for the shadow stage and ran class v3 at half its power limit; the worst MH per watt of every card measured, a 2017 card that cannot pay its own power on any tariff",
|
||
"hive": {
|
||
"core_mhz": null,
|
||
"mem_mhz": null,
|
||
"pl_w": null,
|
||
"label": "stock (rented card; Pascal has no clock lock; no measured tune point)"
|
||
},
|
||
"watts_display": "202.7 (class v4)"
|
||
},
|
||
{
|
||
"generator": "v2",
|
||
"miner": "bench pack, igneum-worker-cuda, class v4 program (3 x 300 dispatches of 2^22)",
|
||
"date": "2026-10-08",
|
||
"by": "measured by the fleet",
|
||
"v4_cost": "not measured (class v4 program only)",
|
||
"tuned": "stock, bench only (rented, no clock control on the host)",
|
||
"card": "NVIDIA RTX 4060 (8 GB)",
|
||
"group": "buy",
|
||
"mh_s": 19.09,
|
||
"watts": null,
|
||
"mh_per_w": null,
|
||
"driver_os": "NVIDIA driver 595.91.07, Ubuntu 24.04 (CUDA 12.8.1 image)",
|
||
"source": "model sweep 2026-10-08, row 18 (a rented card, result cb2-rtx-4060-8-gb-0672-result.json; 09:53Z); the class v4 rerun, 8 October 2026 (result cb4-rtx-4060-8-gb-7165-result.json: the rate on both classes, no watts)",
|
||
"note": "watts not reported by any rented host (four 4060 boards across 7 and 8 October, one machine family, every power field absent; two other hosts never answered ssh); the class v4 rerun on 8 October read the same rate on both classes (19.09 MH/s class v4, 19.094 class v3) and still no watts; by the 4060 Ti pair on the same silicon (+33.6 percent) the class v4 draw is about 80 to 90 W from a class v3 draw of about 60 to 70 W under the 115 W limit, an estimate until an owner measures at the wall.12 h; SM 2,732 MHz mean, memory 8,251 MHz, 57 C, no throttle reason; self-test PASS (96 of 96 vector lanes); the class v5 kit holds the rate (19.11 MH/s, fingerprint matched); read ceiling 30.2 MH/s, the hash at 0.63 of it (the 128-bit bus: the independent-read line binds, as on the 2070 Super). Repeats the 7 October row (19.09 then, 19.10 now)",
|
||
"hive": {
|
||
"core_mhz": null,
|
||
"mem_mhz": null,
|
||
"pl_w": null,
|
||
"label": "stock (rented card, no clock control on the host; no measured tune point)"
|
||
}
|
||
},
|
||
{
|
||
"generator": "v2",
|
||
"miner": "bench pack, igneum-worker-cuda, class v4 program (3 x 300 dispatches of 2^22)",
|
||
"date": "2026-10-08",
|
||
"by": "measured by the fleet",
|
||
"v4_cost": "not measured (class v4 program only)",
|
||
"tuned": "stock, bench only (rented, no clock control on the host)",
|
||
"card": "NVIDIA RTX 2060 (6 GB)",
|
||
"group": "buy",
|
||
"mh_s": 14.13,
|
||
"watts": 127,
|
||
"mh_per_w": 0.117,
|
||
"driver_os": "NVIDIA driver 580.159.03, Ubuntu 24.04 (CUDA 12.8.1 image)",
|
||
"source": "model sweep 2026-10-08, row 19 (a rented card, result cb2-rtx-2060-0673-result.json; 09:55Z); the class v4 watts rerun, 8 October 2026 (result cb4-rtx-2060-0819-result.json, the v4-devnet-epoch0 pack, sub-version 3, three runs of about 30 s, the class v3 pack paired on the same host)",
|
||
"note": "rented single-card host, 0.15 h; power.draw mean 120.6 W (max 124.6, limit 160 W; no power average on Turing), SM 1,948 MHz mean, memory 6,801 MHz, 69 C, no throttle reason; self-test PASS (96 of 96 vector lanes); the class v5 kit holds the rate (14.14 MH/s, fingerprint matched); read ceiling 16.1 MH/s, the hash at 0.88 of it. The floor of the list and the smallest card on it: the class v4 set fits with 4.6 GB spare; the same Turing per-watt floor as the 2070 Super and the 2080 Ti, so every Turing card earns the same per watt and only the absolute rate differs. Class v4 watts (8 October 2026, the rerun, self-test PASS): 127 W at 14.9 MH/s, 0.117 MH per watt; the class v3 pack on the same host read 124.9 W at the same rate, so the shadow premium on this card is +1.7 percent of watts for no rate. the 12 GB variant on a 130 W host cap (stock 185), 5 percent over the morning's 6 GB board (its memory runs faster), so the rate reads as a range; the cap absorbs the premium with the SM giving 7 percent of its clock; the Turing floor under class v4 is 0.09 to 0.12 MH per watt: every Turing card mines at a loss on a real tariff",
|
||
"hive": {
|
||
"core_mhz": null,
|
||
"mem_mhz": null,
|
||
"pl_w": null,
|
||
"label": "stock (rented card, no clock control on the host; no measured tune point)"
|
||
},
|
||
"watts_display": "127 (class v4)",
|
||
"mh_s_display": "14 to 15 by board (14.90 on this 12 GB board)"
|
||
},
|
||
{
|
||
"generator": "v2",
|
||
"miner": "bench pack, igneum-worker-cuda, class v4 program (3 x 300 dispatches of 2^22)",
|
||
"date": "2026-10-08",
|
||
"by": "measured by the fleet",
|
||
"v4_cost": "not measured (class v4 program only)",
|
||
"tuned": "stock, bench only (rented, no clock control on the host)",
|
||
"card": "NVIDIA RTX 4070 Ti (12 GB)",
|
||
"group": "buy",
|
||
"mh_s": 31.24,
|
||
"watts": 155.3,
|
||
"mh_per_w": 0.201,
|
||
"driver_os": "NVIDIA driver 580.126.09, Ubuntu 24.04 (CUDA 12.8.1 image)",
|
||
"source": "model sweep 2026-10-08, row 20 (a rented card, result cb2-rtx-4070-ti-12-gb-0695-result.json; 09:57Z); the class v4 watts rerun, 8 October 2026 (result cb4-rtx-4070-ti-12-gb-5744-result.json, the v4-devnet-epoch0 pack, sub-version 3, three runs of about 30 s, the class v3 pack paired on the same host)",
|
||
"note": "rented single-card host, 0.18 h; power.draw mean 95.4 W (max 96.7, limit 285 W), SM 2,825 MHz mean, memory 10,251 MHz, 49 C, no throttle reason; self-test PASS (96 of 96 vector lanes); the class v5 kit holds the rate (31.28 MH/s, fingerprint matched); read ceiling 31.7 MH/s, the hash at 0.99 of it. Repeats the 7 October rate to 0.07 percent on another provider at 12 W less; the 192-bit Ada pair (4070 Ti, 4070 Super) land on one number, 31.2 MH/s under 100 W. Class v4 watts (8 October 2026, the rerun on the frozen v4-devnet-epoch0 pack, self-test PASS): 155.3 W at 31.26 MH/s, 0.201 MH per watt; the class v3 pack on the same host read 113.8 W at the same rate, so the shadow premium on this card is +36.5 percent of watts for no rate (the class is memory-bound). the rate matches the morning and 7 October rows on a third host (no host spread on this card); driver 570.169 ran the class v4 pack clean",
|
||
"hive": {
|
||
"core_mhz": null,
|
||
"mem_mhz": null,
|
||
"pl_w": null,
|
||
"label": "stock (rented card, no clock control on the host; no measured tune point)"
|
||
},
|
||
"watts_display": "155.3 (class v4)"
|
||
},
|
||
{
|
||
"generator": "v2",
|
||
"miner": "bench pack, igneum-worker-cuda, class v4 program (3 x 300 dispatches of 2^22)",
|
||
"date": "2026-10-08",
|
||
"by": "measured by the fleet",
|
||
"v4_cost": "not measured (class v4 program only)",
|
||
"tuned": "stock, bench only (rented, no clock control on the host)",
|
||
"card": "NVIDIA L40S (48 GB)",
|
||
"group": "datacentre",
|
||
"mh_s": 56.41,
|
||
"watts": 277.6,
|
||
"mh_per_w": 0.203,
|
||
"driver_os": "NVIDIA driver 570.133.20, Ubuntu 24.04 (CUDA 12.8.1 image)",
|
||
"source": "model sweep 2026-10-08, row 21 (a rented card, result cb2-l40s-48-gb-0890-result.json; 09:57Z); the class v4 watts rerun, 8 October 2026 (result cb4-l40s-48-gb-1574-result.json, the v4-devnet-epoch0 pack, sub-version 3, three runs of about 30 s, the class v3 pack paired on the same host)",
|
||
"note": "rented single-card host, 0.17 h; power.draw mean 220.7 W (max 227.2, limit 350 W), SM 2,520 MHz, memory 9,001 MHz, 45 C, no throttle reason; self-test PASS (96 of 96 vector lanes); the class v5 kit holds the rate (56.51 MH/s, fingerprint matched); read ceiling 57.8 MH/s, the hash at 0.98 of it. Repeats the 7 October row (56.36 then, 56.41 now) at 20 W less on this host; a 384-bit GDDR6 card that lands where the 3090 Ti and the A6000 do at a datacentre price. Driver 570.133, the oldest of the sweep, ran the CUDA 12.8 worker clean: 570 is a safe floor. Class v4 watts (8 October 2026, the rerun, self-test PASS): 277.6 W at 56.4 MH/s, 0.203 MH per watt; the class v3 pack on the same host read 219.3 W at the same rate, so the shadow premium on this card is +26.6 percent of watts for no rate. a sibling board of the morning's host, uncapped; the smallest premium of the uncapped Ada boards, the 142 SMs running the shadow stage inside their idle margin without moving the clock; level with the 4070 Ti and the capped 3080 Ti per watt, at a datacentre price",
|
||
"hive": {
|
||
"core_mhz": null,
|
||
"mem_mhz": null,
|
||
"pl_w": null,
|
||
"label": "stock (rented card, no clock control on the host; no measured tune point)"
|
||
},
|
||
"watts_display": "277.6 (class v4)"
|
||
},
|
||
{
|
||
"generator": "v2",
|
||
"miner": "bench pack, igneum-worker-cuda, class v4 program (3 x 300 dispatches of 2^22)",
|
||
"date": "2026-10-08",
|
||
"by": "measured by the fleet",
|
||
"v4_cost": "not measured (class v4 program only)",
|
||
"tuned": "stock, bench only (rented, no clock control on the host)",
|
||
"card": "NVIDIA RTX 4080 Super (16 GB)",
|
||
"group": "buy",
|
||
"mh_s": 42.6,
|
||
"watts": 195.7,
|
||
"mh_per_w": 0.218,
|
||
"driver_os": "NVIDIA driver 580.126.09, Ubuntu 24.04 (CUDA 12.8.1 image)",
|
||
"source": "model sweep 2026-10-08, row 23 (a rented card, result cb2-rtx-4080-super-16-g-2453-result.json; 10:03Z); the class v4 watts rerun, 8 October 2026 (result cb4-rtx-4080-super-16-g-8479-result.json, the v4-devnet-epoch0 pack, sub-version 3, three runs of about 30 s, the class v3 pack paired on the same host)",
|
||
"note": "rented single-card host, 0.12 h; power.draw mean 134.9 W (max 138.4, limit 320 W), SM 2,740 MHz mean, memory 11,254 MHz, 51 C, no throttle reason; self-test PASS (96 of 96 vector lanes); the class v5 kit holds the rate (42.68 MH/s, fingerprint matched); read ceiling 43.1 MH/s, the hash at 0.99 of it. The 23 Gbps GDDR6X gives it 4.6 percent over the 4080 for 6 W more at the same MH per watt: the Ada 256-bit tier is 41 to 43 MH/s whichever card. Class v4 watts (8 October 2026, the rerun, self-test PASS): 195.7 W at 42.63 MH/s, 0.218 MH per watt; the class v3 pack on the same host read 139.8 W at the same rate, so the shadow premium on this card is +40.0 percent of watts for no rate. a sibling board of the morning's host; the rate and the v3 draw repeat the morning; the Ada 256-bit tier reads 0.22 MH per watt under class v4 whichever card",
|
||
"hive": {
|
||
"core_mhz": null,
|
||
"mem_mhz": null,
|
||
"pl_w": null,
|
||
"label": "stock (rented card, no clock control on the host; no measured tune point)"
|
||
},
|
||
"watts_display": "195.7 (class v4)"
|
||
}
|
||
]
|
||
}
|